app.py

import gradio as gr
import torch
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC, pipeline
import soundfile as sf

# Load models
# Transcription model for Moroccan Darija
processor = Wav2Vec2Processor.from_pretrained("achrafkhannoussi/Wav2Vec2-Large-XLSR-53-Moroccan-Darija")
transcription_model = Wav2Vec2ForCTC.from_pretrained("achrafkhannoussi/Wav2Vec2-Large-XLSR-53-Moroccan-Darija")

# Summarization model
summarizer = pipeline("summarization", model="t5-small")

# Function to transcribe audio using Wav2Vec2
def transcribe_audio(audio_path):
    # Load and preprocess audio
    audio_input, sample_rate = sf.read(audio_path)
    inputs = processor(audio_input, sampling_rate=sample_rate, return_tensors="pt", padding=True)

    # Get predictions
    with torch.no_grad():
        logits = transcription_model(**inputs).logits

    # Decode predictions
    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)[0]
    return transcription

# Function to transcribe and summarize
def transcribe_and_summarize(audio_file):
    # Transcription
    transcription = transcribe_audio(audio_file)

    # Summarization
    summary = summarizer(transcription, max_length=50, min_length=10, do_sample=False)[0]["summary_text"]
    return transcription, summary

# Gradio Interface
inputs = gr.Audio(type="filepath", label="Upload your audio file")
outputs = [
    gr.Textbox(label="Transcription"),
    gr.Textbox(label="Summary")
]

app = gr.Interface(
    fn=transcribe_and_summarize,
    inputs=inputs,
    outputs=outputs,
    title="Moroccan Darija Audio Transcription and Summarization",
    description="Upload an audio file in Moroccan Darija to get its transcription and a summarized version of the content."
)

# Launch the app
if __name__ == "__main__":
    app.launch()