# import whisper
# import gradio as gr

# model = whisper.load_model("small")

# def transcribe(audio):
    
#     #time.sleep(3)
#     # load audio and pad/trim it to fit 30 seconds
#     audio = whisper.load_audio(audio)
#     audio = whisper.pad_or_trim(audio)

#     # make log-Mel spectrogram and move to the same device as the model
#     mel = whisper.log_mel_spectrogram(audio).to(model.device)

#     # detect the spoken language
#     _, probs = model.detect_language(mel)
#     print(f"Detected language: {max(probs, key=probs.get)}")

#     # decode the audio
#     options = whisper.DecodingOptions(fp16 = False)
#     result = whisper.decode(model, mel, options)
#     return result.text
    
    
 
# gr.Interface(
#     title = 'Product Recommendation System Text', 
#     fn=transcribe, 
#     inputs=[
#         gr.inputs.Audio(source="microphone", type="filepath")
#     ],
#     outputs=[
#         "textbox"
#     ],
#     live=True).launch()
import whisper
import gradio as gr

model = whisper.load_model("small")

def transcribe(audio):
    # Load audio and pad/trim it to fit 30 seconds
    audio = whisper.load_audio(audio)
    audio = whisper.pad_or_trim(audio)

    # Convert to log-Mel spectrogram
    mel = whisper.log_mel_spectrogram(audio).to(model.device)

    # Detect the spoken language
    _, probs = model.detect_language(mel)
    print(f"Detected language: {max(probs, key=probs.get)}")

    # Decode the audio
    options = whisper.DecodingOptions(fp16=False)
    result = whisper.decode(model, mel, options)
    return result.text

# Update Gradio interface for the new version
gr.Interface(
    title='Product Recommendation System Text', 
    fn=transcribe, 
    inputs=gr.Audio(type="filepath"),  # Removed 'source' argument
    outputs=gr.Textbox(),
    live=True
).launch()