app.py

import whisper
import gradio as gr

# load model and processor

processor = WhisperProcessor.from_pretrained("openai/whisper-medium")

model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-medium")

model.config.forced_decoder_ids = None

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 = 'Talk to NP', 
#     fn=transcribe, 
#     inputs=[
#         gr.inputs.Audio(source="microphone", type="filepath")
#     ],
#     outputs=[
#         "textbox"
#     ],
#     live=True).launch()


def speech_to_text(speech):
    text = asr(speech)["text"]
    return text


def text_to_sentiment(text):
    return classifier(text)[0]["label"]


demo = gr.Blocks()

with demo:
    audio_file = gr.Audio(type="filepath")
    text1 = gr.Textbox()
    text2 = gr.Textbox()

    b1 = gr.Button("Transcribe audio")
    b2 = gr.Button("Summarize")

    b1.click(transcribe, inputs=audio_file, outputs=text)
    b2.click(text_to_sentiment, inputs=text1, outputs=text)

demo.launch()