Yasaman commited on
Commit
f53feee
·
1 Parent(s): e6d1975

Upload 2 files

Browse files
Files changed (2) hide show
  1. app.ipynb +46 -0
  2. requirements.txt.txt +3 -0
app.ipynb ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": []
7
+ },
8
+ "kernelspec": {
9
+ "name": "python3",
10
+ "display_name": "Python 3"
11
+ },
12
+ "language_info": {
13
+ "name": "python"
14
+ }
15
+ },
16
+ "cells": [
17
+ {
18
+ "cell_type": "code",
19
+ "execution_count": null,
20
+ "metadata": {
21
+ "id": "o2EjqHT7vvJv"
22
+ },
23
+ "outputs": [],
24
+ "source": [
25
+ "from transformers import pipeline\n",
26
+ "import gradio as gr\n",
27
+ "\n",
28
+ "pipe = pipeline(model=\"Yasaman/whisper_fa\")\n",
29
+ "\n",
30
+ "def transcribe(audio):\n",
31
+ " text = pipe(audio)[\"text\"]\n",
32
+ " return text\n",
33
+ "\n",
34
+ "iface = gr.Interface(\n",
35
+ " fn=transcribe, \n",
36
+ " inputs=gr.Audio(source=\"microphone\", type=\"filepath\"), \n",
37
+ " outputs=\"text\",\n",
38
+ " title=\"Whisper Small Persian\",\n",
39
+ " description=\"Realtime demo for Persian speech recognition using a fine-tuned Whisper small model.\",\n",
40
+ ")\n",
41
+ "\n",
42
+ "iface.launch()"
43
+ ]
44
+ }
45
+ ]
46
+ }
requirements.txt.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ transformers
2
+ torch
3
+ #pytube