app.py

import gradio as gr
from transformers import Wav2Vec2Processor, Wav2Vec2ForCTC
import torch

# Load the model and processor
processor = Wav2Vec2Processor.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn")
model = Wav2Vec2ForCTC.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-chinese-zh-cn")

# Function to transcribe the audio
def transcribe_audio(audio):
    input_values = processor(audio["array"], sampling_rate=audio["sampling_rate"], return_tensors="pt").input_values

    # Inference
    with torch.no_grad():
        logits = model(input_values).logits

    # Decode the transcription
    predicted_ids = torch.argmax(logits, dim=-1)
    transcription = processor.batch_decode(predicted_ids)

    return transcription[0]  # Since we're only handling one audio file

# Set up the Gradio interface
interface = gr.Interface(
    fn=transcribe_audio,
    inputs=gr.Audio(source="microphone", type="filepath"),  # Accept audio files
    outputs="text",
    title="Chinese Audio Transcription",
    description="Upload or record an audio file to transcribe it into Chinese."
)

# Launch the interface
interface.launch()