app.py

from transformers import pipeline
asr = pipeline(task="automatic-speech-recognition",
               model="distil-whisper/distil-small.en")
import os
import gradio as gr
from pydub import AudioSegment

demo = gr.Blocks()
def transcribe_speech(filepath):
    if filepath is None:
        gr.Warning("No audio found, please retry.")
        return ""

    # Load audio using pydub
    audio = AudioSegment.from_file(filepath)
    chunk_length_ms = 30 * 1000  # 30 seconds
    chunks = [audio[i:i + chunk_length_ms] for i in range(0, len(audio), chunk_length_ms)]

    full_transcription = ""

    for i, chunk in enumerate(chunks):
        # Export chunk to temporary wav file
        chunk_path = f"chunk_{i}.wav"
        chunk.export(chunk_path, format="wav")

        # Transcribe the chunk
        result = asr(chunk_path)
        full_transcription += result["text"] + " "

        # Clean up (optional)
        os.remove(chunk_path)

    return full_transcription.strip()
    
mic_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(sources="microphone",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never")

file_transcribe = gr.Interface(
    fn=transcribe_speech,
    inputs=gr.Audio(sources="upload",
                    type="filepath"),
    outputs=gr.Textbox(label="Transcription",
                       lines=3),
    allow_flagging="never",)

with demo:
    gr.TabbedInterface(
        [mic_transcribe,
         file_transcribe],
        ["Transcribe Microphone",
         "Transcribe Audio File"],
    )
server_port = int(os.environ.get("PORT", 7860))
demo.launch(share=True, 
            server_port=server_port)