Ai-audio / app.py
Athspi's picture
Update app.py
f8b81a1 verified
raw
history blame
1.08 kB
import gradio as gr
from faster_whisper import WhisperModel
# Load the Faster Whisper model
model_name = "Systran/faster-whisper-large-v3"
model = WhisperModel(model_name, device="cpu") # Use "cuda" if you have a GPU
# Define a transcription function
def transcribe_audio(audio_file):
try:
segments, info = model.transcribe(audio_file, beam_size=5) # Customize parameters as needed
transcription = " ".join([segment.text for segment in segments])
return transcription
except Exception as e:
return f"Error: {str(e)}"
# Create Gradio interface
interface = gr.Interface(
fn=transcribe_audio,
inputs=gr.Audio(source="upload", type="filepath", label="Upload Audio"),
outputs=gr.Textbox(label="Transcription"),
title="Sinhala Audio-to-Text Transcription",
description="Upload an audio file and get the transcription in Sinhala using the Faster Whisper model.",
allow_flagging="never"
)
# Launch the Gradio app
if __name__ == "__main__":
interface.launch(server_name="0.0.0.0", server_port=7860, share=True)