Commit
•
c080f5c
1
Parent(s):
d3012a5
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
|
| 2 |
+
|
| 3 |
+
from flask import Flask, render_template, request
|
| 4 |
+
from speechbrain.pretrained import WhisperASR
|
| 5 |
+
|
| 6 |
+
app = Flask(__name__)
|
| 7 |
+
|
| 8 |
+
asr_model = WhisperASR.from_hparams(
|
| 9 |
+
source="speechbrain/asr-whisper-large-v2-commonvoice-fa",
|
| 10 |
+
savedir="pretrained_models/asr-whisper-large-v2-commonvoice-fa"
|
| 11 |
+
)
|
| 12 |
+
|
| 13 |
+
html_template = """
|
| 14 |
+
<!DOCTYPE html>
|
| 15 |
+
<html lang="en">
|
| 16 |
+
<head>
|
| 17 |
+
<meta charset="UTF-8">
|
| 18 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 19 |
+
<title>Speech Transcription</title>
|
| 20 |
+
</head>
|
| 21 |
+
<body>
|
| 22 |
+
<h1>Speech Transcription</h1>
|
| 23 |
+
<form action="/transcribe" method="post" enctype="multipart/form-data">
|
| 24 |
+
<label for="audio_file">Select an audio file:</label>
|
| 25 |
+
<input type="file" name="audio_file" accept=".wav, .mp3">
|
| 26 |
+
<button type="submit">Transcribe</button>
|
| 27 |
+
</form>
|
| 28 |
+
|
| 29 |
+
{% if error %}
|
| 30 |
+
<p style="color: red;">{{ error }}</p>
|
| 31 |
+
{% endif %}
|
| 32 |
+
|
| 33 |
+
{% if transcription %}
|
| 34 |
+
<h2>Transcription Result:</h2>
|
| 35 |
+
<p>{{ transcription }}</p>
|
| 36 |
+
{% endif %}
|
| 37 |
+
</body>
|
| 38 |
+
</html>
|
| 39 |
+
"""
|
| 40 |
+
|
| 41 |
+
@app.route('/')
|
| 42 |
+
def index():
|
| 43 |
+
return html_template
|
| 44 |
+
|
| 45 |
+
@app.route('/transcribe', methods=['POST'])
|
| 46 |
+
def transcribe():
|
| 47 |
+
if 'audio_file' not in request.files:
|
| 48 |
+
return render_template_string(html_template, error='No file part')
|
| 49 |
+
|
| 50 |
+
audio_file = request.files['audio_file']
|
| 51 |
+
|
| 52 |
+
if audio_file.filename == '':
|
| 53 |
+
return render_template_string(html_template, error='No selected file')
|
| 54 |
+
|
| 55 |
+
try:
|
| 56 |
+
transcription = asr_model.transcribe_file(audio_file)
|
| 57 |
+
return render_template_string(html_template, transcription=transcription)
|
| 58 |
+
|
| 59 |
+
except Exception as e:
|
| 60 |
+
return render_template_string(html_template, error=f'Error during transcription: {str(e)}')
|
| 61 |
+
|
| 62 |
+
if __name__ == '__main__':
|
| 63 |
+
app.run(debug=True)
|