|
|
--- |
|
|
language: ja |
|
|
tags: |
|
|
- audio |
|
|
- automatic-speech-recognition |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Kotoba-Whisper: kotoba-whisper-v1.0 for Whisper cpp |
|
|
This repository contains the model weights for [kotoba-tech/kotoba-whisper-v1.0](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0) |
|
|
converted to [GGML](https://github.com/ggerganov/ggml) format. GGML is the weight format expected by C/C++ packages |
|
|
such as [Whisper.cpp](https://github.com/ggerganov/whisper.cpp), for which we provide an example below. |
|
|
|
|
|
## Usage |
|
|
Kotoba-Whisper can be run with the [Whisper.cpp](https://github.com/ggerganov/whisper.cpp) package with the original |
|
|
sequential long-form transcription algorithm. |
|
|
|
|
|
Steps for getting started: |
|
|
|
|
|
1. Clone the Whisper.cpp repository: |
|
|
``` |
|
|
git clone https://github.com/ggerganov/whisper.cpp.git |
|
|
cd whisper.cpp |
|
|
``` |
|
|
2. Download the GGML weights for `kotoba-tech/kotoba-whisper-v1.0`: |
|
|
|
|
|
```bash |
|
|
wget https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/resolve/main/ggml-kotoba-whisper-v1.0.bin -P ./models |
|
|
``` |
|
|
|
|
|
3. Run inference using the provided sample audio: |
|
|
|
|
|
```bash |
|
|
wget https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/resolve/main/sample_ja_speech.wav |
|
|
make -j && ./main -m models/ggml-kotoba-whisper-v1.0.bin -f sample_ja_speech.wav --output-file transcription --output-json |
|
|
``` |
|
|
|
|
|
Note that it runs only with 16-bit WAV files, so make sure to convert your input before running the tool. For example, you can use ffmpeg like this: |
|
|
``` |
|
|
ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav |
|
|
``` |
|
|
|
|
|
### Benchmark |
|
|
We measure the inference speed of different kotoba-whisper-v1.0 implementations with four different Japanese speech audio on MacBook Pro with the following spec: |
|
|
- Apple M2 Pro |
|
|
- 32GB |
|
|
- 14-inch, 2023 |
|
|
- OS Sonoma Version 14.4.1 (23E224) |
|
|
|
|
|
| audio file | audio duration (min)| [whisper.cpp](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml) (sec) | [faster-whisper](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-faster) (sec)| [hf pipeline](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0) (sec) |
|
|
|--------|------|-----|------|---| |
|
|
|audio 1 | 50.3 | 581 | 2601 | | |
|
|
|audio 2 | 5.6 | 41 | 73 | | |
|
|
|audio 3 | 4.9 | 30 | 141 | | |
|
|
|audio 4 | 5.6 | 35 | 126 | | |
|
|
|
|
|
|
|
|
### Quantized Model |
|
|
To use the quantized model, download the quantized GGML weights: |
|
|
|
|
|
```bash |
|
|
wget https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0-ggml/resolve/main/ggml-kotoba-whisper-v1.0-q5_0.bin -P ./models |
|
|
``` |
|
|
|
|
|
Run inference on the sample audio: |
|
|
```bash |
|
|
make -j && ./main -m models/ggml-kotoba-whisper-v1.0-q5_0.bin -f sample_ja_speech.wav --output-file transcription.quantized --output-json |
|
|
``` |
|
|
|
|
|
Note that the benchmark results are almost identical to the raw non-quantized model weight. |
|
|
|
|
|
|
|
|
## Model Details |
|
|
|
|
|
For more information about the kotoba-whisper-v1.0, refer to the original [model card](https://huggingface.co/kotoba-tech/kotoba-whisper-v1.0). |
|
|
|
