{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "dk50gnECjLjp",
"outputId": "34adfe71-1472-4ee8-a9db-60523bf88d1a"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting sacrebleu\n",
" Downloading sacrebleu-2.5.1-py3-none-any.whl.metadata (51 kB)\n",
"\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/51.8 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.8/51.8 kB\u001b[0m \u001b[31m3.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting portalocker (from sacrebleu)\n",
" Downloading portalocker-3.2.0-py3-none-any.whl.metadata (8.7 kB)\n",
"Requirement already satisfied: regex in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (2024.11.6)\n",
"Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (0.9.0)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (2.0.2)\n",
"Collecting colorama (from sacrebleu)\n",
" Downloading colorama-0.4.6-py2.py3-none-any.whl.metadata (17 kB)\n",
"Requirement already satisfied: lxml in /usr/local/lib/python3.11/dist-packages (from sacrebleu) (5.4.0)\n",
"Downloading sacrebleu-2.5.1-py3-none-any.whl (104 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m104.1/104.1 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
"Downloading portalocker-3.2.0-py3-none-any.whl (22 kB)\n",
"Installing collected packages: portalocker, colorama, sacrebleu\n",
"Successfully installed colorama-0.4.6 portalocker-3.2.0 sacrebleu-2.5.1\n"
]
}
],
"source": [
"!pip install sacrebleu"
]
},
{
"cell_type": "code",
"source": [
"!pip install gradio ffmpeg"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "2iz7pUMFuY-l",
"outputId": "e31be326-04af-4213-baa6-ae0e28b45ab7"
},
"execution_count": 2,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: gradio in /usr/local/lib/python3.11/dist-packages (5.38.2)\n",
"Collecting ffmpeg\n",
" Downloading ffmpeg-1.4.tar.gz (5.1 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: aiofiles<25.0,>=22.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (24.1.0)\n",
"Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (4.9.0)\n",
"Requirement already satisfied: brotli>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (1.1.0)\n",
"Requirement already satisfied: fastapi<1.0,>=0.115.2 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.116.1)\n",
"Requirement already satisfied: ffmpy in /usr/local/lib/python3.11/dist-packages (from gradio) (0.6.1)\n",
"Requirement already satisfied: gradio-client==1.11.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (1.11.0)\n",
"Requirement already satisfied: groovy~=0.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.1.2)\n",
"Requirement already satisfied: httpx<1.0,>=0.24.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.28.1)\n",
"Requirement already satisfied: huggingface-hub>=0.28.1 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.34.3)\n",
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.1.6)\n",
"Requirement already satisfied: markupsafe<4.0,>=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.0.2)\n",
"Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.0.2)\n",
"Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (3.11.1)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from gradio) (25.0)\n",
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.2.2)\n",
"Requirement already satisfied: pillow<12.0,>=8.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (11.3.0)\n",
"Requirement already satisfied: pydantic<2.12,>=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.11.7)\n",
"Requirement already satisfied: pydub in /usr/local/lib/python3.11/dist-packages (from gradio) (0.25.1)\n",
"Requirement already satisfied: python-multipart>=0.0.18 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.0.20)\n",
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (6.0.2)\n",
"Requirement already satisfied: ruff>=0.9.3 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.12.5)\n",
"Requirement already satisfied: safehttpx<0.2.0,>=0.1.6 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.1.6)\n",
"Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (2.10.0)\n",
"Requirement already satisfied: starlette<1.0,>=0.40.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.47.2)\n",
"Requirement already satisfied: tomlkit<0.14.0,>=0.12.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.13.3)\n",
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.16.0)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (4.14.1)\n",
"Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.11/dist-packages (from gradio) (0.35.0)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.11.0->gradio) (2025.3.0)\n",
"Requirement already satisfied: websockets<16.0,>=10.0 in /usr/local/lib/python3.11/dist-packages (from gradio-client==1.11.0->gradio) (15.0.1)\n",
"Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.11/dist-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
"Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.11/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.11/dist-packages (from httpx<1.0,>=0.24.1->gradio) (2025.7.14)\n",
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.11/dist-packages (from httpx<1.0,>=0.24.1->gradio) (1.0.9)\n",
"Requirement already satisfied: h11>=0.16 in /usr/local/lib/python3.11/dist-packages (from httpcore==1.*->httpx<1.0,>=0.24.1->gradio) (0.16.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (3.18.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (2.32.3)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (4.67.1)\n",
"Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub>=0.28.1->gradio) (1.1.5)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas<3.0,>=1.0->gradio) (2025.2)\n",
"Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (2.33.2)\n",
"Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<2.12,>=2.0->gradio) (0.4.1)\n",
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (8.2.1)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.11/dist-packages (from typer<1.0,>=0.12->gradio) (13.9.4)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.17.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.19.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.28.1->gradio) (3.4.2)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->huggingface-hub>=0.28.1->gradio) (2.5.0)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
"Building wheels for collected packages: ffmpeg\n",
" Building wheel for ffmpeg (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for ffmpeg: filename=ffmpeg-1.4-py3-none-any.whl size=6083 sha256=4dccf8185b38521d5a4bb388563dd90ad11db98d010fabcd2fbf6881755f8891\n",
" Stored in directory: /root/.cache/pip/wheels/56/30/c5/576bdd729f3bc062d62a551be7fefd6ed2f761901568171e4e\n",
"Successfully built ffmpeg\n",
"Installing collected packages: ffmpeg\n",
"Successfully installed ffmpeg-1.4\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!pip install -r /content/requirements.txt"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "0Ze3q0CqjYMp",
"outputId": "4040b2a7-645b-4ac4-9047-91f8fbf62bd8"
},
"execution_count": 5,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git (from nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Cloning https://github.com/NVIDIA/NeMo.git to /tmp/pip-install-7j0ourtb/nemo-toolkit_f8f688ddcc76456592aa95f279152eb7\n",
" Running command git clone --filter=blob:none --quiet https://github.com/NVIDIA/NeMo.git /tmp/pip-install-7j0ourtb/nemo-toolkit_f8f688ddcc76456592aa95f279152eb7\n",
" Resolved https://github.com/NVIDIA/NeMo.git to commit 99e5dac685f88718f81281c0a1f51ca0ac2cb64d\n",
" Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: librosa in /usr/local/lib/python3.11/dist-packages (from -r /content/requirements.txt (line 2)) (0.11.0)\n",
"Requirement already satisfied: soundfile in /usr/local/lib/python3.11/dist-packages (from -r /content/requirements.txt (line 3)) (0.13.1)\n",
"Requirement already satisfied: moviepy==1.0.3 in /usr/local/lib/python3.11/dist-packages (from -r /content/requirements.txt (line 4)) (1.0.3)\n",
"Requirement already satisfied: torch in /usr/local/lib/python3.11/dist-packages (from -r /content/requirements.txt (line 5)) (2.6.0+cu124)\n",
"Requirement already satisfied: decorator<5.0,>=4.0.2 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (4.4.2)\n",
"Requirement already satisfied: tqdm<5.0,>=4.11.2 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (4.67.1)\n",
"Requirement already satisfied: requests<3.0,>=2.8.1 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (2.32.3)\n",
"Requirement already satisfied: proglog<=1.0.0 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (0.1.12)\n",
"Requirement already satisfied: numpy>=1.17.3 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (2.0.2)\n",
"Requirement already satisfied: imageio<3.0,>=2.5 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (2.37.0)\n",
"Requirement already satisfied: imageio-ffmpeg>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from moviepy==1.0.3->-r /content/requirements.txt (line 4)) (0.6.0)\n",
"Collecting fsspec==2024.12.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\n",
"Requirement already satisfied: huggingface_hub>=0.24 in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.34.3)\n",
"Requirement already satisfied: numba in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.60.0)\n",
"Collecting onnx>=1.7.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading onnx-1.18.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.9 kB)\n",
"Requirement already satisfied: protobuf~=5.29.5 in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (5.29.5)\n",
"Requirement already satisfied: python-dateutil in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.9.0.post0)\n",
"Collecting ruamel.yaml (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading ruamel.yaml-0.18.14-py3-none-any.whl.metadata (24 kB)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.6.1)\n",
"Requirement already satisfied: setuptools>=70.0.0 in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (75.2.0)\n",
"Requirement already satisfied: tensorboard in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.18.0)\n",
"Requirement already satisfied: text-unidecode in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.3)\n",
"Collecting wget (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading wget-3.2.zip (10 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: wrapt in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.17.2)\n",
"Requirement already satisfied: audioread>=2.1.9 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (3.0.1)\n",
"Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (1.16.1)\n",
"Requirement already satisfied: joblib>=1.0 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (1.5.1)\n",
"Requirement already satisfied: pooch>=1.1 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (1.8.2)\n",
"Requirement already satisfied: soxr>=0.3.2 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (0.5.0.post1)\n",
"Requirement already satisfied: typing_extensions>=4.1.1 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (4.14.1)\n",
"Requirement already satisfied: lazy_loader>=0.1 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (0.4)\n",
"Requirement already satisfied: msgpack>=1.0 in /usr/local/lib/python3.11/dist-packages (from librosa->-r /content/requirements.txt (line 2)) (1.1.1)\n",
"Requirement already satisfied: cffi>=1.0 in /usr/local/lib/python3.11/dist-packages (from soundfile->-r /content/requirements.txt (line 3)) (1.17.1)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (3.18.0)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (3.5)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (3.1.6)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.4.127 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.4.127 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.4.127 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cudnn-cu12==9.1.0.70 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cublas-cu12==12.4.5.8 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cufft-cu12==11.2.1.3 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-curand-cu12==10.3.5.147 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting nvidia-cusolver-cu12==11.6.1.9 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Collecting nvidia-cusparse-cu12==12.3.1.170 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl.metadata (1.6 kB)\n",
"Requirement already satisfied: nvidia-cusparselt-cu12==0.6.2 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (0.6.2)\n",
"Requirement already satisfied: nvidia-nccl-cu12==2.21.5 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (2.21.5)\n",
"Requirement already satisfied: nvidia-nvtx-cu12==12.4.127 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (12.4.127)\n",
"Collecting nvidia-nvjitlink-cu12==12.4.127 (from torch->-r /content/requirements.txt (line 5))\n",
" Downloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Requirement already satisfied: triton==3.2.0 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (3.2.0)\n",
"Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.11/dist-packages (from torch->-r /content/requirements.txt (line 5)) (1.13.1)\n",
"Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.11/dist-packages (from sympy==1.13.1->torch->-r /content/requirements.txt (line 5)) (1.3.0)\n",
"Collecting attrdict (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading attrdict-2.0.1-py2.py3-none-any.whl.metadata (6.7 kB)\n",
"Collecting cdifflib==1.2.6 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading cdifflib-1.2.6.tar.gz (11 kB)\n",
" Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n",
" Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n",
" Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: einops in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.8.1)\n",
"Collecting janome (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading Janome-0.5.0-py2.py3-none-any.whl.metadata (2.6 kB)\n",
"Requirement already satisfied: jieba in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.42.1)\n",
"Collecting kornia (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading kornia-0.8.1-py2.py3-none-any.whl.metadata (17 kB)\n",
"Requirement already satisfied: matplotlib in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.10.0)\n",
"Collecting nemo_text_processing (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading nemo_text_processing-1.1.0-py3-none-any.whl.metadata (7.3 kB)\n",
"Requirement already satisfied: nltk in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.9.1)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.2.2)\n",
"Collecting pypinyin (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pypinyin-0.55.0-py2.py3-none-any.whl.metadata (12 kB)\n",
"Collecting pypinyin-dict (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pypinyin_dict-0.9.0-py2.py3-none-any.whl.metadata (3.8 kB)\n",
"Requirement already satisfied: seaborn in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.13.2)\n",
"Collecting braceexpand (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading braceexpand-0.1.7-py2.py3-none-any.whl.metadata (3.0 kB)\n",
"Requirement already satisfied: editdistance in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.8.1)\n",
"Collecting jiwer<4.0.0,>=3.1.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading jiwer-3.1.0-py3-none-any.whl.metadata (2.6 kB)\n",
"Collecting kaldi-python-io (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading kaldi-python-io-1.2.2.tar.gz (8.8 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting lhotse!=1.31.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading lhotse-1.30.3-py3-none-any.whl.metadata (18 kB)\n",
"Collecting marshmallow (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading marshmallow-4.0.0-py3-none-any.whl.metadata (7.4 kB)\n",
"Collecting optuna (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading optuna-4.4.0-py3-none-any.whl.metadata (17 kB)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (25.0)\n",
"Collecting pyannote.core (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pyannote.core-5.0.0-py3-none-any.whl.metadata (1.4 kB)\n",
"Collecting pyannote.metrics (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pyannote.metrics-3.2.1-py3-none-any.whl.metadata (1.3 kB)\n",
"Requirement already satisfied: pydub in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.25.1)\n",
"Collecting pyloudnorm (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pyloudnorm-0.1.1-py3-none-any.whl.metadata (5.6 kB)\n",
"Collecting resampy (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading resampy-0.4.3-py3-none-any.whl.metadata (3.0 kB)\n",
"Collecting sox<=1.5.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading sox-1.5.0.tar.gz (63 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m63.9/63.9 kB\u001b[0m \u001b[31m5.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting texterrors<1.0.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading texterrors-0.5.1.tar.gz (23 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting whisper_normalizer (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading whisper_normalizer-0.1.12-py3-none-any.whl.metadata (7.9 kB)\n",
"Collecting num2words (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading num2words-0.5.14-py3-none-any.whl.metadata (13 kB)\n",
"Collecting numpy>=1.17.3 (from moviepy==1.0.3->-r /content/requirements.txt (line 4))\n",
" Downloading numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (61 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.0/61.0 kB\u001b[0m \u001b[31m6.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: datasets in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.0.0)\n",
"Requirement already satisfied: inflect in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (7.5.0)\n",
"Collecting mediapy==1.1.6 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading mediapy-1.1.6-py3-none-any.whl.metadata (4.8 kB)\n",
"Collecting sacremoses>=0.0.43 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading sacremoses-0.1.1-py3-none-any.whl.metadata (8.3 kB)\n",
"Requirement already satisfied: sentencepiece<1.0.0 in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.2.0)\n",
"Requirement already satisfied: cloudpickle in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.1.1)\n",
"Collecting fiddle (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading fiddle-0.3.0-py3-none-any.whl.metadata (2.3 kB)\n",
"Collecting hydra-core<=1.3.2,>1.3 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading hydra_core-1.3.2-py3-none-any.whl.metadata (5.5 kB)\n",
"Collecting lightning<=2.4.0,>2.2.1 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading lightning-2.4.0-py3-none-any.whl.metadata (38 kB)\n",
"Requirement already satisfied: omegaconf<=2.3 in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.3.0)\n",
"Requirement already satisfied: peft in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.16.0)\n",
"Collecting torchmetrics>=0.11.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading torchmetrics-1.8.0-py3-none-any.whl.metadata (21 kB)\n",
"Collecting transformers<=4.52.0,>=4.51.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading transformers-4.51.3-py3-none-any.whl.metadata (38 kB)\n",
"Requirement already satisfied: wandb in /usr/local/lib/python3.11/dist-packages (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.21.0)\n",
"Collecting webdataset>=0.2.86 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading webdataset-1.0.2-py3-none-any.whl.metadata (12 kB)\n",
"Collecting bitsandbytes==0.46.0 (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading bitsandbytes-0.46.0-py3-none-manylinux_2_24_x86_64.whl.metadata (10 kB)\n",
"Requirement already satisfied: ipython in /usr/local/lib/python3.11/dist-packages (from mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (7.34.0)\n",
"Requirement already satisfied: Pillow in /usr/local/lib/python3.11/dist-packages (from mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (11.3.0)\n",
"Requirement already satisfied: pycparser in /usr/local/lib/python3.11/dist-packages (from cffi>=1.0->soundfile->-r /content/requirements.txt (line 3)) (2.22)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub>=0.24->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (6.0.2)\n",
"Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.11/dist-packages (from huggingface_hub>=0.24->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.1.5)\n",
"Requirement already satisfied: antlr4-python3-runtime==4.9.* in /usr/local/lib/python3.11/dist-packages (from hydra-core<=1.3.2,>1.3->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.9.3)\n",
"Requirement already satisfied: click>=8.1.8 in /usr/local/lib/python3.11/dist-packages (from jiwer<4.0.0,>=3.1.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (8.2.1)\n",
"Collecting rapidfuzz>=3.9.7 (from jiwer<4.0.0,>=3.1.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading rapidfuzz-3.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
"Collecting cytoolz>=0.10.1 (from lhotse!=1.31.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading cytoolz-1.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.6 kB)\n",
"Collecting intervaltree>=3.1.0 (from lhotse!=1.31.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading intervaltree-3.1.0.tar.gz (32 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: tabulate>=0.8.1 in /usr/local/lib/python3.11/dist-packages (from lhotse!=1.31.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.9.0)\n",
"Collecting lilcom>=1.1.0 (from lhotse!=1.31.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading lilcom-1.8.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.2 kB)\n",
"Collecting lightning-utilities<2.0,>=0.10.0 (from lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading lightning_utilities-0.15.0-py3-none-any.whl.metadata (5.7 kB)\n",
"Collecting packaging (from nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading packaging-24.2-py3-none-any.whl.metadata (3.2 kB)\n",
"Collecting pytorch-lightning (from lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pytorch_lightning-2.5.2-py3-none-any.whl.metadata (21 kB)\n",
"Requirement already satisfied: llvmlite<0.44,>=0.43.0dev0 in /usr/local/lib/python3.11/dist-packages (from numba->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.43.0)\n",
"Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.11/dist-packages (from pooch>=1.1->librosa->-r /content/requirements.txt (line 2)) (4.3.8)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests<3.0,>=2.8.1->moviepy==1.0.3->-r /content/requirements.txt (line 4)) (3.4.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests<3.0,>=2.8.1->moviepy==1.0.3->-r /content/requirements.txt (line 4)) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests<3.0,>=2.8.1->moviepy==1.0.3->-r /content/requirements.txt (line 4)) (2.5.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests<3.0,>=2.8.1->moviepy==1.0.3->-r /content/requirements.txt (line 4)) (2025.7.14)\n",
"Requirement already satisfied: regex in /usr/local/lib/python3.11/dist-packages (from sacremoses>=0.0.43->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2024.11.6)\n",
"Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.11/dist-packages (from scikit-learn->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.6.0)\n",
"Collecting pybind11 (from texterrors<1.0.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Using cached pybind11-3.0.0-py3-none-any.whl.metadata (10.0 kB)\n",
"Collecting plac (from texterrors<1.0.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading plac-1.4.5-py2.py3-none-any.whl.metadata (5.9 kB)\n",
"Collecting loguru (from texterrors<1.0.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading loguru-0.7.3-py3-none-any.whl.metadata (22 kB)\n",
"Requirement already satisfied: termcolor in /usr/local/lib/python3.11/dist-packages (from texterrors<1.0.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.1.0)\n",
"Collecting Levenshtein (from texterrors<1.0.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading levenshtein-0.27.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.6 kB)\n",
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers<=4.52.0,>=4.51.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.21.4)\n",
"Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers<=4.52.0,>=4.51.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.5.3)\n",
"Requirement already satisfied: six in /usr/local/lib/python3.11/dist-packages (from attrdict->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.17.0)\n",
"Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.11/dist-packages (from datasets->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (18.1.0)\n",
"Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.11/dist-packages (from datasets->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.3.8)\n",
"Requirement already satisfied: xxhash in /usr/local/lib/python3.11/dist-packages (from datasets->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.5.0)\n",
"Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.11/dist-packages (from datasets->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.70.16)\n",
"Requirement already satisfied: absl-py in /usr/local/lib/python3.11/dist-packages (from fiddle->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.4.0)\n",
"Requirement already satisfied: graphviz in /usr/local/lib/python3.11/dist-packages (from fiddle->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.21)\n",
"Collecting libcst (from fiddle->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading libcst-1.8.2-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (15 kB)\n",
"Requirement already satisfied: more_itertools>=8.5.0 in /usr/local/lib/python3.11/dist-packages (from inflect->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (10.7.0)\n",
"Requirement already satisfied: typeguard>=4.0.1 in /usr/local/lib/python3.11/dist-packages (from inflect->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.4.4)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.11/dist-packages (from jinja2->torch->-r /content/requirements.txt (line 5)) (3.0.2)\n",
"Collecting kornia_rs>=0.1.9 (from kornia->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading kornia_rs-0.1.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (11 kB)\n",
"Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.3.3)\n",
"Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.11/dist-packages (from matplotlib->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.12.1)\n",
"Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.11/dist-packages (from matplotlib->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.59.0)\n",
"Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.4.8)\n",
"Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.11/dist-packages (from matplotlib->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.2.3)\n",
"Collecting pynini==2.1.6.post1 (from nemo_text_processing->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pynini-2.1.6.post1-cp311-cp311-manylinux_2_28_x86_64.whl.metadata (4.8 kB)\n",
"Collecting docopt>=0.6.2 (from num2words->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading docopt-0.6.2.tar.gz (25 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Collecting alembic>=1.5.0 (from optuna->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading alembic-1.16.4-py3-none-any.whl.metadata (7.3 kB)\n",
"Collecting colorlog (from optuna->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading colorlog-6.9.0-py3-none-any.whl.metadata (10 kB)\n",
"Requirement already satisfied: sqlalchemy>=1.4.2 in /usr/local/lib/python3.11/dist-packages (from optuna->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.0.42)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2025.2)\n",
"Requirement already satisfied: psutil in /usr/local/lib/python3.11/dist-packages (from peft->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (5.9.5)\n",
"Requirement already satisfied: accelerate>=0.21.0 in /usr/local/lib/python3.11/dist-packages (from peft->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.9.0)\n",
"Requirement already satisfied: sortedcontainers>=2.0.4 in /usr/local/lib/python3.11/dist-packages (from pyannote.core->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.4.0)\n",
"Collecting pyannote.database>=4.0.1 (from pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading pyannote.database-5.1.3-py3-none-any.whl.metadata (1.1 kB)\n",
"Requirement already satisfied: future>=0.16.0 in /usr/local/lib/python3.11/dist-packages (from pyloudnorm->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.0.0)\n",
"Collecting ruamel.yaml.clib>=0.2.7 (from ruamel.yaml->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (2.7 kB)\n",
"Requirement already satisfied: grpcio>=1.48.2 in /usr/local/lib/python3.11/dist-packages (from tensorboard->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.74.0)\n",
"Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.11/dist-packages (from tensorboard->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.8.2)\n",
"Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /usr/local/lib/python3.11/dist-packages (from tensorboard->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.7.2)\n",
"Requirement already satisfied: werkzeug>=1.0.1 in /usr/local/lib/python3.11/dist-packages (from tensorboard->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.1.3)\n",
"Requirement already satisfied: gitpython!=3.1.29,>=1.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.1.45)\n",
"Requirement already satisfied: pydantic<3 in /usr/local/lib/python3.11/dist-packages (from wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.11.7)\n",
"Requirement already satisfied: sentry-sdk>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.34.0)\n",
"Collecting indic-numtowords (from whisper_normalizer->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading indic_numtowords-1.0.2.tar.gz (24 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: Mako in /usr/lib/python3/dist-packages (from alembic>=1.5.0->optuna->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.1.3)\n",
"Requirement already satisfied: toolz>=0.8.0 in /usr/local/lib/python3.11/dist-packages (from cytoolz>=0.10.1->lhotse!=1.31.0->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.12.1)\n",
"Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.11/dist-packages (from fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.12.15)\n",
"Requirement already satisfied: gitdb<5,>=4.0.1 in /usr/local/lib/python3.11/dist-packages (from gitpython!=3.1.29,>=1.0.0->wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.0.12)\n",
"Requirement already satisfied: typer>=0.12.1 in /usr/local/lib/python3.11/dist-packages (from pyannote.database>=4.0.1->pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.16.0)\n",
"Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<3->wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.33.2 in /usr/local/lib/python3.11/dist-packages (from pydantic<3->wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.33.2)\n",
"Requirement already satisfied: typing-inspection>=0.4.0 in /usr/local/lib/python3.11/dist-packages (from pydantic<3->wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.4.1)\n",
"Requirement already satisfied: greenlet>=1 in /usr/local/lib/python3.11/dist-packages (from sqlalchemy>=1.4.2->optuna->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.2.3)\n",
"Collecting jedi>=0.16 (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1))\n",
" Downloading jedi-0.19.2-py2.py3-none-any.whl.metadata (22 kB)\n",
"Requirement already satisfied: pickleshare in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.7.5)\n",
"Requirement already satisfied: traitlets>=4.2 in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (5.7.1)\n",
"Requirement already satisfied: prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0 in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.0.51)\n",
"Requirement already satisfied: pygments in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.19.2)\n",
"Requirement already satisfied: backcall in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.2.0)\n",
"Requirement already satisfied: matplotlib-inline in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.1.7)\n",
"Requirement already satisfied: pexpect>4.3 in /usr/local/lib/python3.11/dist-packages (from ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (4.9.0)\n",
"Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (2.6.1)\n",
"Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.4.0)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (25.3.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.7.0)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (6.6.3)\n",
"Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.3.2)\n",
"Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.11/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<2026.0,>=2022.5.0->lightning<=2.4.0,>2.2.1->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.20.1)\n",
"Requirement already satisfied: smmap<6,>=3.0.1 in /usr/local/lib/python3.11/dist-packages (from gitdb<5,>=4.0.1->gitpython!=3.1.29,>=1.0.0->wandb->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (5.0.2)\n",
"Requirement already satisfied: parso<0.9.0,>=0.8.4 in /usr/local/lib/python3.11/dist-packages (from jedi>=0.16->ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.8.4)\n",
"Requirement already satisfied: ptyprocess>=0.5 in /usr/local/lib/python3.11/dist-packages (from pexpect>4.3->ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.7.0)\n",
"Requirement already satisfied: wcwidth in /usr/local/lib/python3.11/dist-packages (from prompt-toolkit!=3.0.0,!=3.0.1,<3.1.0,>=2.0.0->ipython->mediapy==1.1.6->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.2.13)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.11/dist-packages (from typer>=0.12.1->pyannote.database>=4.0.1->pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.11/dist-packages (from typer>=0.12.1->pyannote.database>=4.0.1->pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (13.9.4)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.11/dist-packages (from rich>=10.11.0->typer>=0.12.1->pyannote.database>=4.0.1->pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (3.0.0)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.11/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer>=0.12.1->pyannote.database>=4.0.1->pyannote.metrics->nemo_toolkit@ git+https://github.com/NVIDIA/NeMo.git->nemo_toolkit[asr,tts]@ git+https://github.com/NVIDIA/NeMo.git->-r /content/requirements.txt (line 1)) (0.1.2)\n",
"Downloading fsspec-2024.12.0-py3-none-any.whl (183 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m183.9/183.9 kB\u001b[0m \u001b[31m12.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cublas_cu12-12.4.5.8-py3-none-manylinux2014_x86_64.whl (363.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m363.4/363.4 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_cupti_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (13.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m13.8/13.8 MB\u001b[0m \u001b[31m69.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_nvrtc_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (24.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.6/24.6 MB\u001b[0m \u001b[31m36.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cuda_runtime_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (883 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m883.7/883.7 kB\u001b[0m \u001b[31m49.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cudnn_cu12-9.1.0.70-py3-none-manylinux2014_x86_64.whl (664.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m664.8/664.8 MB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cufft_cu12-11.2.1.3-py3-none-manylinux2014_x86_64.whl (211.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m211.5/211.5 MB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_curand_cu12-10.3.5.147-py3-none-manylinux2014_x86_64.whl (56.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.3/56.3 MB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cusolver_cu12-11.6.1.9-py3-none-manylinux2014_x86_64.whl (127.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m127.9/127.9 MB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_cusparse_cu12-12.3.1.170-py3-none-manylinux2014_x86_64.whl (207.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m207.5/207.5 MB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.1/21.1 MB\u001b[0m \u001b[31m83.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading bitsandbytes-0.46.0-py3-none-manylinux_2_24_x86_64.whl (67.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.0/67.0 MB\u001b[0m \u001b[31m10.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading mediapy-1.1.6-py3-none-any.whl (24 kB)\n",
"Downloading hydra_core-1.3.2-py3-none-any.whl (154 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.5/154.5 kB\u001b[0m \u001b[31m17.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading jiwer-3.1.0-py3-none-any.whl (22 kB)\n",
"Downloading lhotse-1.30.3-py3-none-any.whl (851 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m851.4/851.4 kB\u001b[0m \u001b[31m61.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading lightning-2.4.0-py3-none-any.whl (810 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m811.0/811.0 kB\u001b[0m \u001b[31m57.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (18.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m18.3/18.3 MB\u001b[0m \u001b[31m113.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading onnx-1.18.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (17.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m17.6/17.6 MB\u001b[0m \u001b[31m110.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading packaging-24.2-py3-none-any.whl (65 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m65.5/65.5 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading sacremoses-0.1.1-py3-none-any.whl (897 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m897.5/897.5 kB\u001b[0m \u001b[31m62.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading torchmetrics-1.8.0-py3-none-any.whl (981 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m981.9/981.9 kB\u001b[0m \u001b[31m62.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading transformers-4.51.3-py3-none-any.whl (10.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.4/10.4 MB\u001b[0m \u001b[31m126.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading webdataset-1.0.2-py3-none-any.whl (74 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.0/75.0 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading attrdict-2.0.1-py2.py3-none-any.whl (9.9 kB)\n",
"Downloading braceexpand-0.1.7-py2.py3-none-any.whl (5.9 kB)\n",
"Downloading fiddle-0.3.0-py3-none-any.whl (419 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m419.8/419.8 kB\u001b[0m \u001b[31m39.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading Janome-0.5.0-py2.py3-none-any.whl (19.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m19.7/19.7 MB\u001b[0m \u001b[31m102.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading kornia-0.8.1-py2.py3-none-any.whl (1.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m70.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading marshmallow-4.0.0-py3-none-any.whl (48 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.4/48.4 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nemo_text_processing-1.1.0-py3-none-any.whl (2.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.7/2.7 MB\u001b[0m \u001b[31m86.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pynini-2.1.6.post1-cp311-cp311-manylinux_2_28_x86_64.whl (154.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m154.8/154.8 MB\u001b[0m \u001b[31m7.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading num2words-0.5.14-py3-none-any.whl (163 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m163.5/163.5 kB\u001b[0m \u001b[31m17.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading optuna-4.4.0-py3-none-any.whl (395 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m395.9/395.9 kB\u001b[0m \u001b[31m36.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.core-5.0.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.5/58.5 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.metrics-3.2.1-py3-none-any.whl (51 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m51.4/51.4 kB\u001b[0m \u001b[31m5.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyloudnorm-0.1.1-py3-none-any.whl (9.6 kB)\n",
"Downloading pypinyin-0.55.0-py2.py3-none-any.whl (840 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m840.2/840.2 kB\u001b[0m \u001b[31m64.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pypinyin_dict-0.9.0-py2.py3-none-any.whl (9.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.5/9.5 MB\u001b[0m \u001b[31m107.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading resampy-0.4.3-py3-none-any.whl (3.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m88.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ruamel.yaml-0.18.14-py3-none-any.whl (118 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m118.6/118.6 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading whisper_normalizer-0.1.12-py3-none-any.whl (36 kB)\n",
"Downloading alembic-1.16.4-py3-none-any.whl (247 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m247.0/247.0 kB\u001b[0m \u001b[31m25.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading cytoolz-1.0.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m86.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading kornia_rs-0.1.9-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.8/2.8 MB\u001b[0m \u001b[31m106.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading lightning_utilities-0.15.0-py3-none-any.whl (29 kB)\n",
"Downloading lilcom-1.8.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (94 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m94.3/94.3 kB\u001b[0m \u001b[31m10.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyannote.database-5.1.3-py3-none-any.whl (48 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m48.1/48.1 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading rapidfuzz-3.13.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m106.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ruamel.yaml.clib-0.2.12-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (739 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m739.1/739.1 kB\u001b[0m \u001b[31m57.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading colorlog-6.9.0-py3-none-any.whl (11 kB)\n",
"Downloading levenshtein-0.27.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (161 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m161.7/161.7 kB\u001b[0m \u001b[31m17.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading libcst-1.8.2-cp311-cp311-manylinux_2_28_x86_64.whl (2.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m96.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading loguru-0.7.3-py3-none-any.whl (61 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.6/61.6 kB\u001b[0m \u001b[31m6.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading plac-1.4.5-py2.py3-none-any.whl (22 kB)\n",
"Using cached pybind11-3.0.0-py3-none-any.whl (292 kB)\n",
"Downloading pytorch_lightning-2.5.2-py3-none-any.whl (825 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m825.4/825.4 kB\u001b[0m \u001b[31m64.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading jedi-0.19.2-py2.py3-none-any.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m86.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hBuilding wheels for collected packages: nemo_toolkit, cdifflib, sox, texterrors, kaldi-python-io, wget, docopt, intervaltree, indic-numtowords\n",
" Building wheel for nemo_toolkit (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for nemo_toolkit: filename=nemo_toolkit-2.5.0rc0-py3-none-any.whl size=6695427 sha256=e4b8c6ec82f80736078f1dd8002c7d2e4b75301683768efa04f6ac0992751861\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-dbvcspwx/wheels/54/fe/f9/6404063304730f13faa8f01956f227f95c4ac57fb3e014fc33\n",
" Building wheel for cdifflib (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for cdifflib: filename=cdifflib-1.2.6-cp311-cp311-linux_x86_64.whl size=28738 sha256=4bdca626c55f7324fbe18c4ebf94b51d7650e5ad7ae687d974acd3361feffbe0\n",
" Stored in directory: /root/.cache/pip/wheels/61/25/f2/4ee06fe9d0bcb43991be6302633001497862ff216060e9361f\n",
" Building wheel for sox (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for sox: filename=sox-1.5.0-py3-none-any.whl size=40036 sha256=753ac105077971b2b5a3f74afdcf4b9a656b04c0c1d4ccc5d85d354f060b31dc\n",
" Stored in directory: /root/.cache/pip/wheels/74/89/93/023fcdacaec4e5471e78b43992515e8500cc2505b307e2e6b7\n",
" Building wheel for texterrors (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for texterrors: filename=texterrors-0.5.1-cp311-cp311-linux_x86_64.whl size=1174756 sha256=1ffe6efa5c4e45f16e0864a8e82d2224657fb1c3fb6fbbfa7dc0ea9a6723545a\n",
" Stored in directory: /root/.cache/pip/wheels/6f/94/c8/7edaa578fc800d26e3fda18fba557a4218ab553d078ee51b46\n",
" Building wheel for kaldi-python-io (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for kaldi-python-io: filename=kaldi_python_io-1.2.2-py3-none-any.whl size=8953 sha256=cae8e1ff1c1d82876fc6b60406fc049d493de28b80037f9aaeedfea02c15d2e2\n",
" Stored in directory: /root/.cache/pip/wheels/f2/86/7b/eec1bb7dc63b8aab5da6317609313873e6e75f065b65f3c29c\n",
" Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for wget: filename=wget-3.2-py3-none-any.whl size=9655 sha256=bacacc224397132f28b651e7ff2c1756dfd5e718db937ceb229aa3138b308b9f\n",
" Stored in directory: /root/.cache/pip/wheels/40/b3/0f/a40dbd1c6861731779f62cc4babcb234387e11d697df70ee97\n",
" Building wheel for docopt (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for docopt: filename=docopt-0.6.2-py2.py3-none-any.whl size=13706 sha256=83eb7a77c51d0f8472afc102c275f5fa4b13bac1d87ebe2e8f57ac2d073b9039\n",
" Stored in directory: /root/.cache/pip/wheels/1a/b0/8c/4b75c4116c31f83c8f9f047231251e13cc74481cca4a78a9ce\n",
" Building wheel for intervaltree (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for intervaltree: filename=intervaltree-3.1.0-py2.py3-none-any.whl size=26098 sha256=94bdbc67af9fe3357ae6720738fb53ca69726437eb80780c3218a0724fa04225\n",
" Stored in directory: /root/.cache/pip/wheels/31/d7/d9/eec6891f78cac19a693bd40ecb8365d2f4613318c145ec9816\n",
" Building wheel for indic-numtowords (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for indic-numtowords: filename=indic_numtowords-1.0.2-py3-none-any.whl size=39214 sha256=55526afa9d00f3664532f6d2612d43da94d7e1102fafc2ba219a74a2bbd09afc\n",
" Stored in directory: /root/.cache/pip/wheels/09/b1/af/e78074d6002f3805735ab2eb3c0c42222b68db37e7face6b25\n",
"Successfully built nemo_toolkit cdifflib sox texterrors kaldi-python-io wget docopt intervaltree indic-numtowords\n",
"Installing collected packages: wget, plac, janome, docopt, braceexpand, sacremoses, ruamel.yaml.clib, rapidfuzz, pypinyin, pynini, pybind11, packaging, nvidia-nvjitlink-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, numpy, num2words, marshmallow, loguru, libcst, kornia_rs, jedi, intervaltree, indic-numtowords, fsspec, cytoolz, colorlog, cdifflib, attrdict, whisper_normalizer, webdataset, sox, ruamel.yaml, pypinyin-dict, onnx, nvidia-cusparse-cu12, nvidia-cudnn-cu12, lilcom, lightning-utilities, Levenshtein, kaldi-python-io, jiwer, hydra-core, fiddle, alembic, texterrors, resampy, pyloudnorm, pyannote.core, optuna, nvidia-cusolver-cu12, transformers, pyannote.database, mediapy, torchmetrics, pyannote.metrics, nemo_toolkit, nemo_text_processing, lhotse, kornia, bitsandbytes, pytorch-lightning, lightning\n",
" Attempting uninstall: packaging\n",
" Found existing installation: packaging 25.0\n",
" Uninstalling packaging-25.0:\n",
" Successfully uninstalled packaging-25.0\n",
" Attempting uninstall: nvidia-nvjitlink-cu12\n",
" Found existing installation: nvidia-nvjitlink-cu12 12.5.82\n",
" Uninstalling nvidia-nvjitlink-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-nvjitlink-cu12-12.5.82\n",
" Attempting uninstall: nvidia-curand-cu12\n",
" Found existing installation: nvidia-curand-cu12 10.3.6.82\n",
" Uninstalling nvidia-curand-cu12-10.3.6.82:\n",
" Successfully uninstalled nvidia-curand-cu12-10.3.6.82\n",
" Attempting uninstall: nvidia-cufft-cu12\n",
" Found existing installation: nvidia-cufft-cu12 11.2.3.61\n",
" Uninstalling nvidia-cufft-cu12-11.2.3.61:\n",
" Successfully uninstalled nvidia-cufft-cu12-11.2.3.61\n",
" Attempting uninstall: nvidia-cuda-runtime-cu12\n",
" Found existing installation: nvidia-cuda-runtime-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-runtime-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-runtime-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cuda-nvrtc-cu12\n",
" Found existing installation: nvidia-cuda-nvrtc-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-nvrtc-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-nvrtc-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cuda-cupti-cu12\n",
" Found existing installation: nvidia-cuda-cupti-cu12 12.5.82\n",
" Uninstalling nvidia-cuda-cupti-cu12-12.5.82:\n",
" Successfully uninstalled nvidia-cuda-cupti-cu12-12.5.82\n",
" Attempting uninstall: nvidia-cublas-cu12\n",
" Found existing installation: nvidia-cublas-cu12 12.5.3.2\n",
" Uninstalling nvidia-cublas-cu12-12.5.3.2:\n",
" Successfully uninstalled nvidia-cublas-cu12-12.5.3.2\n",
" Attempting uninstall: numpy\n",
" Found existing installation: numpy 2.0.2\n",
" Uninstalling numpy-2.0.2:\n",
" Successfully uninstalled numpy-2.0.2\n",
" Attempting uninstall: fsspec\n",
" Found existing installation: fsspec 2025.3.0\n",
" Uninstalling fsspec-2025.3.0:\n",
" Successfully uninstalled fsspec-2025.3.0\n",
" Attempting uninstall: nvidia-cusparse-cu12\n",
" Found existing installation: nvidia-cusparse-cu12 12.5.1.3\n",
" Uninstalling nvidia-cusparse-cu12-12.5.1.3:\n",
" Successfully uninstalled nvidia-cusparse-cu12-12.5.1.3\n",
" Attempting uninstall: nvidia-cudnn-cu12\n",
" Found existing installation: nvidia-cudnn-cu12 9.3.0.75\n",
" Uninstalling nvidia-cudnn-cu12-9.3.0.75:\n",
" Successfully uninstalled nvidia-cudnn-cu12-9.3.0.75\n",
" Attempting uninstall: nvidia-cusolver-cu12\n",
" Found existing installation: nvidia-cusolver-cu12 11.6.3.83\n",
" Uninstalling nvidia-cusolver-cu12-11.6.3.83:\n",
" Successfully uninstalled nvidia-cusolver-cu12-11.6.3.83\n",
" Attempting uninstall: transformers\n",
" Found existing installation: transformers 4.54.1\n",
" Uninstalling transformers-4.54.1:\n",
" Successfully uninstalled transformers-4.54.1\n",
"\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
"opencv-python-headless 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\n",
"gcsfs 2025.3.0 requires fsspec==2025.3.0, but you have fsspec 2024.12.0 which is incompatible.\n",
"opencv-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\n",
"thinc 8.3.6 requires numpy<3.0.0,>=2.0.0, but you have numpy 1.26.4 which is incompatible.\n",
"opencv-contrib-python 4.12.0.88 requires numpy<2.3.0,>=2; python_version >= \"3.9\", but you have numpy 1.26.4 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed Levenshtein-0.27.1 alembic-1.16.4 attrdict-2.0.1 bitsandbytes-0.46.0 braceexpand-0.1.7 cdifflib-1.2.6 colorlog-6.9.0 cytoolz-1.0.1 docopt-0.6.2 fiddle-0.3.0 fsspec-2024.12.0 hydra-core-1.3.2 indic-numtowords-1.0.2 intervaltree-3.1.0 janome-0.5.0 jedi-0.19.2 jiwer-3.1.0 kaldi-python-io-1.2.2 kornia-0.8.1 kornia_rs-0.1.9 lhotse-1.30.3 libcst-1.8.2 lightning-2.4.0 lightning-utilities-0.15.0 lilcom-1.8.1 loguru-0.7.3 marshmallow-4.0.0 mediapy-1.1.6 nemo_text_processing-1.1.0 nemo_toolkit-2.5.0rc0 num2words-0.5.14 numpy-1.26.4 nvidia-cublas-cu12-12.4.5.8 nvidia-cuda-cupti-cu12-12.4.127 nvidia-cuda-nvrtc-cu12-12.4.127 nvidia-cuda-runtime-cu12-12.4.127 nvidia-cudnn-cu12-9.1.0.70 nvidia-cufft-cu12-11.2.1.3 nvidia-curand-cu12-10.3.5.147 nvidia-cusolver-cu12-11.6.1.9 nvidia-cusparse-cu12-12.3.1.170 nvidia-nvjitlink-cu12-12.4.127 onnx-1.18.0 optuna-4.4.0 packaging-24.2 plac-1.4.5 pyannote.core-5.0.0 pyannote.database-5.1.3 pyannote.metrics-3.2.1 pybind11-3.0.0 pyloudnorm-0.1.1 pynini-2.1.6.post1 pypinyin-0.55.0 pypinyin-dict-0.9.0 pytorch-lightning-2.5.2 rapidfuzz-3.13.0 resampy-0.4.3 ruamel.yaml-0.18.14 ruamel.yaml.clib-0.2.12 sacremoses-0.1.1 sox-1.5.0 texterrors-0.5.1 torchmetrics-1.8.0 transformers-4.51.3 webdataset-1.0.2 wget-3.2 whisper_normalizer-0.1.12\n"
]
},
{
"output_type": "display_data",
"data": {
"application/vnd.colab-display-data+json": {
"pip_warning": {
"packages": [
"numpy",
"packaging"
]
},
"id": "7e83fbb67c064ccbbbe6bb9808504f46"
}
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"%%writefile app.py\n",
"import gradio as gr\n",
"import os\n",
"import tempfile\n",
"import subprocess\n",
"import librosa\n",
"import soundfile as sf\n",
"import torch\n",
"from pathlib import Path\n",
"import traceback\n",
"from typing import List, Dict, Tuple, Optional\n",
"import time\n",
"\n",
"# Install required packages\n",
"def install_requirements():\n",
" \"\"\"Install required packages if not already installed\"\"\"\n",
" try:\n",
" import nemo\n",
" print(\"NeMo already installed\")\n",
" except ImportError:\n",
" print(\"Installing NeMo...\")\n",
" subprocess.run([\n",
" \"pip\", \"install\",\n",
" \"nemo_toolkit[asr,tts] @ git+https://github.com/NVIDIA/NeMo.git\"\n",
" ], check=True)\n",
"\n",
" try:\n",
" import moviepy\n",
" print(\"MoviePy already installed\")\n",
" except ImportError:\n",
" print(\"Installing MoviePy...\")\n",
" subprocess.run([\"pip\", \"install\", \"moviepy\"], check=True)\n",
"\n",
"# Try to install requirements\n",
"try:\n",
" install_requirements()\n",
" from nemo.collections.speechlm2.models import SALM\n",
" import moviepy.editor as mp\n",
" DEPENDENCIES_AVAILABLE = True\n",
"except Exception as e:\n",
" print(f\"Warning: Could not install dependencies: {e}\")\n",
" DEPENDENCIES_AVAILABLE = False\n",
"\n",
"class VideoQASummarizer:\n",
" def __init__(self):\n",
" self.model = None\n",
" self.current_transcript = \"\"\n",
" self.model_loaded = False\n",
" self.device = self._get_device()\n",
"\n",
" def _get_device(self):\n",
" \"\"\"Determine the best available device\"\"\"\n",
" if torch.cuda.is_available():\n",
" device = torch.device(\"cuda\")\n",
" print(f\"CUDA available: {torch.cuda.get_device_name()}\")\n",
" print(f\"GPU Memory: {torch.cuda.get_device_properties(0).total_memory / 1024**3:.1f} GB\")\n",
" return device\n",
" else:\n",
" print(\"CUDA not available, using CPU\")\n",
" return torch.device(\"cpu\")\n",
"\n",
" def load_model(self):\n",
" \"\"\"Load the Canary-Qwen-2.5B model with CUDA support\"\"\"\n",
" if not DEPENDENCIES_AVAILABLE:\n",
" return \"Error: Required dependencies not available. Please install manually.\"\n",
"\n",
" try:\n",
" if self.model is None:\n",
" print(f\"Loading Canary-Qwen-2.5B model on {self.device}...\")\n",
"\n",
" # Load model with device specification\n",
" self.model = SALM.from_pretrained('nvidia/canary-qwen-2.5b')\n",
"\n",
" # Move model to GPU if available\n",
" if self.device.type == \"cuda\":\n",
" self.model = self.model.to(self.device)\n",
" print(f\"Model moved to GPU: {torch.cuda.get_device_name()}\")\n",
"\n",
" # Enable mixed precision for better GPU performance\n",
" if hasattr(self.model, 'half'):\n",
" # Use half precision for inference to save memory\n",
" self.model = self.model.half()\n",
" print(\"Enabled half precision for better GPU performance\")\n",
"\n",
" # Set model to evaluation mode for inference\n",
" self.model.eval()\n",
"\n",
" self.model_loaded = True\n",
"\n",
" # Display memory usage if using GPU\n",
" if self.device.type == \"cuda\":\n",
" memory_allocated = torch.cuda.memory_allocated() / 1024**3\n",
" memory_reserved = torch.cuda.memory_reserved() / 1024**3\n",
" return f\"Model loaded successfully on GPU!\\nMemory allocated: {memory_allocated:.2f} GB\\nMemory reserved: {memory_reserved:.2f} GB\"\n",
" else:\n",
" return \"Model loaded successfully on CPU!\"\n",
" return \"Model already loaded.\"\n",
" except Exception as e:\n",
" error_msg = f\"Error loading model: {str(e)}\"\n",
" print(error_msg)\n",
" print(traceback.format_exc())\n",
" return error_msg\n",
"\n",
" def extract_audio_from_video(self, video_path: str) -> str:\n",
" \"\"\"Extract audio from video file\"\"\"\n",
" try:\n",
" # Create temporary audio file\n",
" temp_audio = tempfile.NamedTemporaryFile(delete=False, suffix='.wav')\n",
" temp_audio_path = temp_audio.name\n",
" temp_audio.close()\n",
"\n",
" # Load video and extract audio\n",
" video = mp.VideoFileClip(video_path)\n",
" audio = video.audio\n",
"\n",
" # Write audio to temporary file\n",
" audio.write_audiofile(temp_audio_path, verbose=False, logger=None)\n",
"\n",
" # Clean up\n",
" audio.close()\n",
" video.close()\n",
"\n",
" return temp_audio_path\n",
" except Exception as e:\n",
" raise Exception(f\"Error extracting audio: {str(e)}\")\n",
"\n",
" def split_audio_by_duration(self, audio_path: str, max_duration: int = 30) -> List[str]:\n",
" \"\"\"Split long audio files into smaller chunks\"\"\"\n",
" try:\n",
" # Load audio to check duration\n",
" audio, sr = librosa.load(audio_path, sr=16000)\n",
" total_duration = len(audio) / sr\n",
"\n",
" if total_duration <= max_duration:\n",
" return [audio_path]\n",
"\n",
" # Split audio into chunks\n",
" chunk_paths = []\n",
" chunk_samples = max_duration * sr\n",
"\n",
" for i in range(0, len(audio), chunk_samples):\n",
" chunk = audio[i:i + chunk_samples]\n",
"\n",
" # Create temporary file for chunk\n",
" temp_chunk = tempfile.NamedTemporaryFile(delete=False, suffix=f'_chunk_{i//chunk_samples}.wav')\n",
" chunk_path = temp_chunk.name\n",
" temp_chunk.close()\n",
"\n",
" # Save chunk\n",
" sf.write(chunk_path, chunk, sr)\n",
" chunk_paths.append(chunk_path)\n",
"\n",
" return chunk_paths\n",
" except Exception as e:\n",
" raise Exception(f\"Error splitting audio: {str(e)}\")\n",
"\n",
" def preprocess_audio(self, audio_path: str) -> str:\n",
" \"\"\"Preprocess audio for the model (ensure correct format)\"\"\"\n",
" try:\n",
" # Load audio\n",
" audio, sr = librosa.load(audio_path, sr=16000) # Resample to 16kHz if needed\n",
"\n",
" # Create new temporary file for processed audio\n",
" temp_processed = tempfile.NamedTemporaryFile(delete=False, suffix='.wav')\n",
" temp_processed_path = temp_processed.name\n",
" temp_processed.close()\n",
"\n",
" # Save processed audio\n",
" sf.write(temp_processed_path, audio, 16000)\n",
"\n",
" return temp_processed_path\n",
" except Exception as e:\n",
" raise Exception(f\"Error preprocessing audio: {str(e)}\")\n",
"\n",
" def transcribe_audio_chunk(self, audio_path: str) -> str:\n",
" \"\"\"Transcribe a single audio chunk\"\"\"\n",
" try:\n",
" # Preprocess audio\n",
" processed_audio_path = self.preprocess_audio(audio_path)\n",
"\n",
" # Transcribe using ASR mode with increased token limit\n",
" answer_ids = self.model.generate(\n",
" prompts=[\n",
" [{\"role\": \"user\", \"content\": f\"Transcribe the following: {self.model.audio_locator_tag}\", \"audio\": [processed_audio_path]}]\n",
" ],\n",
" max_new_tokens=2048, # Increased from 512 to handle longer content\n",
" temperature=0.1, # Lower temperature for more consistent transcription\n",
" do_sample=True,\n",
" )\n",
"\n",
" transcript = self.model.tokenizer.ids_to_text(answer_ids[0].cpu())\n",
"\n",
" # Clean up temporary file\n",
" os.unlink(processed_audio_path)\n",
"\n",
" return transcript.strip()\n",
" except Exception as e:\n",
" raise Exception(f\"Error transcribing chunk: {str(e)}\")\n",
"\n",
" def transcribe_audio(self, audio_path: str) -> str:\n",
" \"\"\"Transcribe audio using Canary-Qwen-2.5B in ASR mode with chunking for long files\"\"\"\n",
" try:\n",
" if not self.model_loaded:\n",
" return \"Error: Model not loaded. Please load the model first.\"\n",
"\n",
" # Check audio duration and split if necessary\n",
" audio, sr = librosa.load(audio_path, sr=16000)\n",
" duration = len(audio) / sr\n",
" print(f\"Audio duration: {duration:.2f} seconds\")\n",
"\n",
" if duration > 30: # Split long audio files\n",
" print(\"Long audio detected, splitting into chunks...\")\n",
" chunk_paths = self.split_audio_by_duration(audio_path, max_duration=30)\n",
"\n",
" full_transcript = \"\"\n",
" for i, chunk_path in enumerate(chunk_paths):\n",
" print(f\"Transcribing chunk {i+1}/{len(chunk_paths)}\")\n",
" chunk_transcript = self.transcribe_audio_chunk(chunk_path)\n",
"\n",
" # Clean up chunk transcript (remove model artifacts)\n",
" chunk_transcript = self.clean_transcript(chunk_transcript)\n",
"\n",
" if chunk_transcript:\n",
" full_transcript += chunk_transcript + \" \"\n",
"\n",
" # Clean up chunk file if we created it\n",
" if chunk_path != audio_path:\n",
" os.unlink(chunk_path)\n",
"\n",
" return full_transcript.strip()\n",
" else:\n",
" # Short audio, transcribe directly\n",
" transcript = self.transcribe_audio_chunk(audio_path)\n",
" return self.clean_transcript(transcript)\n",
"\n",
" except Exception as e:\n",
" error_msg = f\"Error during transcription: {str(e)}\"\n",
" print(error_msg)\n",
" print(traceback.format_exc())\n",
" return error_msg\n",
"\n",
" def clean_transcript(self, transcript: str) -> str:\n",
" \"\"\"Clean up transcript by removing model artifacts and formatting issues\"\"\"\n",
" try:\n",
" # Remove common model artifacts\n",
" artifacts_to_remove = [\n",
" \"Sure! Here's the transcription without the timestamps, written as a single paragraph:\",\n",
" \"Here's the transcription:\",\n",
" \"Transcription:\",\n",
" \"<|im_start|>\",\n",
" \"<|im_end|>\",\n",
" \"\",\n",
" ]\n",
"\n",
" cleaned = transcript\n",
" for artifact in artifacts_to_remove:\n",
" cleaned = cleaned.replace(artifact, \"\")\n",
"\n",
" # Remove extra whitespace and normalize\n",
" cleaned = \" \".join(cleaned.split())\n",
"\n",
" # Remove any leading/trailing punctuation issues\n",
" cleaned = cleaned.strip(\" .,!?\")\n",
"\n",
" return cleaned\n",
" except Exception as e:\n",
" print(f\"Error cleaning transcript: {e}\")\n",
" return transcript\n",
"\n",
" def answer_question(self, question: str, transcript: str) -> str:\n",
" \"\"\"Answer questions about the transcript using LLM mode\"\"\"\n",
" try:\n",
" if not self.model_loaded:\n",
" return \"Error: Model not loaded. Please load the model first.\"\n",
"\n",
" if not transcript:\n",
" return \"Error: No transcript available. Please transcribe a video first.\"\n",
"\n",
" # Use LLM mode to answer questions\n",
" prompt = f\"Based on the following transcript, please answer this question: {question}\\n\\nTranscript: {transcript}\"\n",
"\n",
" with self.model.llm.disable_adapter():\n",
" answer_ids = self.model.generate(\n",
" prompts=[[{\"role\": \"user\", \"content\": prompt}]],\n",
" max_new_tokens=1024, # Increased for longer answers\n",
" temperature=0.3,\n",
" do_sample=True,\n",
" )\n",
"\n",
" answer = self.model.tokenizer.ids_to_text(answer_ids[0].cpu())\n",
" return answer.strip()\n",
" except Exception as e:\n",
" error_msg = f\"Error answering question: {str(e)}\"\n",
" print(error_msg)\n",
" print(traceback.format_exc())\n",
" return error_msg\n",
"\n",
" def summarize_transcript(self, transcript: str, summary_type: str = \"general\") -> str:\n",
" \"\"\"Summarize the transcript using LLM mode\"\"\"\n",
" try:\n",
" if not self.model_loaded:\n",
" return \"Error: Model not loaded. Please load the model first.\"\n",
"\n",
" if not transcript:\n",
" return \"Error: No transcript available. Please transcribe a video first.\"\n",
"\n",
" # Create different summary prompts based on type\n",
" if summary_type == \"bullet_points\":\n",
" prompt = f\"Please create a bullet-point summary of the key points from this transcript:\\n\\n{transcript}\"\n",
" elif summary_type == \"detailed\":\n",
" prompt = f\"Please provide a detailed summary of this transcript, including main topics and important details:\\n\\n{transcript}\"\n",
" else: # general\n",
" prompt = f\"Please provide a concise summary of this transcript:\\n\\n{transcript}\"\n",
"\n",
" with self.model.llm.disable_adapter():\n",
" answer_ids = self.model.generate(\n",
" prompts=[[{\"role\": \"user\", \"content\": prompt}]],\n",
" max_new_tokens=1536, # Increased for longer summaries\n",
" temperature=0.3,\n",
" do_sample=True,\n",
" )\n",
"\n",
" summary = self.model.tokenizer.ids_to_text(answer_ids[0].cpu())\n",
" return summary.strip()\n",
" except Exception as e:\n",
" error_msg = f\"Error creating summary: {str(e)}\"\n",
" print(error_msg)\n",
" print(traceback.format_exc())\n",
" return error_msg\n",
"\n",
"# Initialize the model\n",
"qa_summarizer = VideoQASummarizer()\n",
"\n",
"def load_model_interface():\n",
" \"\"\"Interface function to load the model\"\"\"\n",
" return qa_summarizer.load_model()\n",
"\n",
"def process_video(video_file, progress=gr.Progress()):\n",
" \"\"\"Process uploaded video and return transcript\"\"\"\n",
" if video_file is None:\n",
" return \"Please upload a video file.\", \"\"\n",
"\n",
" try:\n",
" progress(0.1, desc=\"Extracting audio from video...\")\n",
" # Extract audio from video\n",
" audio_path = qa_summarizer.extract_audio_from_video(video_file)\n",
"\n",
" progress(0.3, desc=\"Analyzing audio duration...\")\n",
" # Check audio duration for progress estimation\n",
" audio, sr = librosa.load(audio_path, sr=16000)\n",
" duration = len(audio) / sr\n",
"\n",
" progress(0.4, desc=\"Starting transcription...\")\n",
" # Transcribe audio\n",
" transcript = qa_summarizer.transcribe_audio(audio_path)\n",
"\n",
" progress(0.9, desc=\"Finalizing transcript...\")\n",
" # Store transcript for later use\n",
" qa_summarizer.current_transcript = transcript\n",
"\n",
" # Clean up temporary audio file\n",
" if os.path.exists(audio_path):\n",
" os.unlink(audio_path)\n",
"\n",
" progress(1.0, desc=\"Complete!\")\n",
" return f\"Video processed successfully! (Duration: {duration:.1f}s)\", transcript\n",
" except Exception as e:\n",
" error_msg = f\"Error processing video: {str(e)}\"\n",
" print(error_msg)\n",
" print(traceback.format_exc())\n",
" return error_msg, \"\"\n",
"\n",
"def answer_question_interface(question, transcript):\n",
" \"\"\"Interface function to answer questions\"\"\"\n",
" if not question.strip():\n",
" return \"Please enter a question.\"\n",
"\n",
" return qa_summarizer.answer_question(question, transcript or qa_summarizer.current_transcript)\n",
"\n",
"def summarize_interface(transcript, summary_type):\n",
" \"\"\"Interface function to create summaries\"\"\"\n",
" return qa_summarizer.summarize_transcript(transcript or qa_summarizer.current_transcript, summary_type)\n",
"\n",
"# Create Gradio interface\n",
"def create_interface():\n",
" with gr.Blocks(title=\"Video Q&A and Summarizer\", theme=gr.themes.Soft()) as app:\n",
" gr.Markdown(\"\"\"\n",
" # 🎥 Video Question Answering and Summarizer\n",
"\n",
" Upload a video file to transcribe its audio content, then ask questions or generate summaries using NVIDIA's Canary-Qwen-2.5B model.\n",
"\n",
" **Features:**\n",
" - Extract and transcribe audio from video files (handles long videos with chunking)\n",
" - Ask questions about the video content\n",
" - Generate different types of summaries\n",
" - Powered by NVIDIA NeMo Canary-Qwen-2.5B\n",
" \"\"\")\n",
"\n",
" # Model loading section\n",
" with gr.Row():\n",
" gr.Markdown(\"## 🚀 Step 1: Load Model\")\n",
"\n",
" with gr.Row():\n",
" load_btn = gr.Button(\"Load Canary-Qwen-2.5B Model\", variant=\"primary\")\n",
" model_status = gr.Textbox(label=\"Model Status\", interactive=False)\n",
"\n",
" load_btn.click(load_model_interface, outputs=model_status)\n",
"\n",
" # Video processing section\n",
" with gr.Row():\n",
" gr.Markdown(\"## 📹 Step 2: Upload and Process Video\")\n",
"\n",
" with gr.Row():\n",
" with gr.Column():\n",
" video_input = gr.Video(label=\"Upload Video File\")\n",
" process_btn = gr.Button(\"Process Video\", variant=\"primary\")\n",
"\n",
" with gr.Column():\n",
" process_status = gr.Textbox(label=\"Processing Status\", interactive=False)\n",
" transcript_output = gr.Textbox(\n",
" label=\"Transcript\",\n",
" lines=15,\n",
" max_lines=25,\n",
" interactive=False,\n",
" show_copy_button=True\n",
" )\n",
"\n",
" process_btn.click(\n",
" process_video,\n",
" inputs=video_input,\n",
" outputs=[process_status, transcript_output],\n",
" show_progress=True\n",
" )\n",
"\n",
" # Question answering section\n",
" with gr.Row():\n",
" gr.Markdown(\"## ❓ Step 3: Ask Questions\")\n",
"\n",
" with gr.Row():\n",
" with gr.Column():\n",
" question_input = gr.Textbox(\n",
" label=\"Your Question\",\n",
" placeholder=\"What is this video about?\",\n",
" lines=2\n",
" )\n",
" ask_btn = gr.Button(\"Ask Question\", variant=\"secondary\")\n",
"\n",
" with gr.Column():\n",
" answer_output = gr.Textbox(\n",
" label=\"Answer\",\n",
" lines=6,\n",
" interactive=False,\n",
" show_copy_button=True\n",
" )\n",
"\n",
" ask_btn.click(\n",
" answer_question_interface,\n",
" inputs=[question_input, transcript_output],\n",
" outputs=answer_output\n",
" )\n",
"\n",
" # Summarization section\n",
" with gr.Row():\n",
" gr.Markdown(\"## 📝 Step 4: Generate Summary\")\n",
"\n",
" with gr.Row():\n",
" with gr.Column():\n",
" summary_type = gr.Dropdown(\n",
" choices=[\"general\", \"detailed\", \"bullet_points\"],\n",
" value=\"general\",\n",
" label=\"Summary Type\"\n",
" )\n",
" summarize_btn = gr.Button(\"Generate Summary\", variant=\"secondary\")\n",
"\n",
" with gr.Column():\n",
" summary_output = gr.Textbox(\n",
" label=\"Summary\",\n",
" lines=10,\n",
" interactive=False,\n",
" show_copy_button=True\n",
" )\n",
"\n",
" summarize_btn.click(\n",
" summarize_interface,\n",
" inputs=[transcript_output, summary_type],\n",
" outputs=summary_output\n",
" )\n",
"\n",
" # Instructions and tips\n",
" with gr.Row():\n",
" gr.Markdown(\"\"\"\n",
" ## 💡 Tips & Improvements:\n",
"\n",
" 1. **Supported formats**: MP4, AVI, MOV, MKV, and other common video formats\n",
" 2. **Audio quality**: Better audio quality leads to more accurate transcriptions\n",
" 3. **Long videos**: The app now automatically splits long audio files into chunks for complete transcription\n",
" 4. **Processing time**: Longer videos are processed in chunks, which may take more time but ensures completeness\n",
" 5. **Questions**: Be specific with your questions for better answers\n",
" 6. **Summaries**: Choose the summary type that best fits your needs\n",
"\n",
" ## 🔧 GPU & Performance Features:\n",
" - **CUDA GPU Support** - Automatically detects and uses GPU if available\n",
" - **Mixed Precision** - Uses half precision (FP16) on GPU for better performance\n",
" - **Memory Management** - Automatic GPU memory cleanup after each operation\n",
" - **Performance Optimization** - Gradient disabled for inference, caching enabled\n",
" - **Memory Monitoring** - Shows GPU memory usage when model loads\n",
"\n",
" ## 🔧 Recent Fixes:\n",
" - **Increased token limits** for complete transcriptions (4096 tokens for all operations)\n",
" - **Audio chunking** for videos longer than 30 seconds to prevent cutoffs\n",
" - **Improved transcript cleaning** to remove model artifacts\n",
" - **Better progress tracking** during video processing\n",
" - **Copy buttons** for easy text copying\n",
"\n",
" ## ⚠️ Requirements:\n",
" - **CUDA GPU** - Strongly recommended for optimal performance (RTX 3090, 4090, A100, etc.)\n",
" - **GPU Memory** - At least 8GB VRAM recommended for the 2.5B model\n",
" - **PyTorch** - Version 2.6+ with CUDA support for FSDP2\n",
" - **Disk Space** - Sufficient space for temporary audio files and model cache\n",
" \"\"\")\n",
"\n",
" return app\n",
"\n",
"# Launch the application\n",
"if __name__ == \"__main__\":\n",
" app = create_interface()\n",
" app.launch(\n",
" share=True\n",
" )"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "PL2RwMo0lyhG",
"outputId": "07bdf7b6-0639-4069-a919-001a22c150ac"
},
"execution_count": 6,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Overwriting app.py\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"!python app.py"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "6Lpd-Qr0l7YT",
"outputId": "2e450a8d-eca2-47b2-e906-6e1dc31218aa"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"NeMo already installed\n",
"MoviePy already installed\n",
"2025-07-31 19:08:14.606014: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:477] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
"E0000 00:00:1753988894.861095 4326 cuda_dnn.cc:8310] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
"E0000 00:00:1753988894.929380 4326 cuda_blas.cc:1418] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
"2025-07-31 19:08:15.484273: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
"To enable the following instructions: AVX2 AVX512F FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
"error: XDG_RUNTIME_DIR not set in the environment.\n",
"ALSA lib confmisc.c:855:(parse_card) cannot find card '0'\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory\n",
"ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory\n",
"ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory\n",
"ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory\n",
"ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default\n",
"ALSA lib confmisc.c:855:(parse_card) cannot find card '0'\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_card_inum returned error: No such file or directory\n",
"ALSA lib confmisc.c:422:(snd_func_concat) error evaluating strings\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_concat returned error: No such file or directory\n",
"ALSA lib confmisc.c:1334:(snd_func_refer) error evaluating name\n",
"ALSA lib conf.c:5178:(_snd_config_evaluate) function snd_func_refer returned error: No such file or directory\n",
"ALSA lib conf.c:5701:(snd_config_expand) Evaluate error: No such file or directory\n",
"ALSA lib pcm.c:2664:(snd_pcm_open_noupdate) Unknown PCM default\n",
"CUDA available: Tesla T4\n",
"GPU Memory: 14.7 GB\n",
"* Running on local URL: http://127.0.0.1:7860\n",
"* Running on public URL: https://6e0bb20ea085bb1b8d.gradio.live\n",
"\n",
"This share link expires in 1 week. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n",
"Loading Canary-Qwen-2.5B model on cuda...\n",
"[NeMo I 2025-07-31 19:08:52 nemo_logging:393] 1 special tokens added, resize your model accordingly.\n",
"[NeMo I 2025-07-31 19:09:23 nemo_logging:393] LoRA adapter installed: LoraConfig(task_type='CAUSAL_LM', peft_type=, auto_mapping=None, base_model_name_or_path='Qwen/Qwen3-1.7B', revision=None, inference_mode=False, r=128, target_modules=['q_proj', 'v_proj'], exclude_modules=None, lora_alpha=256, lora_dropout=0.01, fan_in_fan_out=False, bias='none', use_rslora=False, modules_to_save=None, init_lora_weights=True, layers_to_transform=None, layers_pattern=None, rank_pattern={}, alpha_pattern={}, megatron_config=None, megatron_core='megatron.core', trainable_token_indices=None, loftq_config={}, eva_config=None, corda_config=None, use_dora=False, use_qalora=False, qalora_group_size=16, layer_replication=None, runtime_config=LoraRuntimeConfig(ephemeral_gpu_offload=False), lora_bias=False)\n",
"[NeMo I 2025-07-31 19:09:23 nemo_logging:393] PADDING: 0\n",
"model.safetensors: 100% 5.12G/5.12G [11:01<00:00, 3.30MB/s]\n",
"Model moved to GPU: Tesla T4\n",
"Enabled half precision for better GPU performance\n",
"Audio duration: 133.21 seconds\n",
"Long audio detected, splitting into chunks...\n",
"Transcribing chunk 1/5\n",
"`generation_config` default values have been modified to match model-specific defaults: {'bos_token_id': 151643}. If this is not desired, please set these values explicitly.\n",
"Transcribing chunk 2/5\n",
"Transcribing chunk 3/5\n",
"Transcribing chunk 4/5\n",
"Transcribing chunk 5/5\n"
]
}
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "NUPpkJjsl90x"
},
"execution_count": null,
"outputs": []
}
]
}