Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
@@ -1,27 +1,19 @@
|
|
|
|
1 |
from transformers import pipeline
|
2 |
|
3 |
-
def
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
audio_path = os.path.join(temp_dir, "temp_audio.wav")
|
9 |
-
|
10 |
-
subprocess.run([
|
11 |
-
"ffmpeg", "-f", "alsa", "-i", "default", "-t", "5", "-ar", "16000", "-ac", "1", audio_path
|
12 |
-
], check=True)
|
13 |
-
|
14 |
-
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base.en")
|
15 |
-
result = transcriber(audio_path)
|
16 |
-
return result["text"]
|
17 |
|
18 |
interface = gr.Interface(
|
19 |
-
fn=
|
20 |
-
inputs=
|
21 |
outputs="text",
|
22 |
-
|
23 |
-
|
|
|
24 |
)
|
25 |
|
26 |
if __name__ == "__main__":
|
27 |
-
interface.launch(
|
|
|
1 |
+
import gradio as gr
|
2 |
from transformers import pipeline
|
3 |
|
4 |
+
def transcribe_audio(audio):
|
5 |
+
transcriber = pipeline("automatic-speech-recognition", model="openai/whisper-base")
|
6 |
+
result = transcriber(audio)
|
7 |
+
return result['text']
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
8 |
|
9 |
interface = gr.Interface(
|
10 |
+
fn=transcribe_audio,
|
11 |
+
inputs=gr.Audio(source="microphone", type="filepath", label="Input Audio"),
|
12 |
outputs="text",
|
13 |
+
live=True,
|
14 |
+
title="Speech to Text - Persian",
|
15 |
+
description="Record your voice in Persian and see the transcription here."
|
16 |
)
|
17 |
|
18 |
if __name__ == "__main__":
|
19 |
+
interface.launch()
|