app.py

import gradio as gr
from transformers import pipeline
import whisper

# Load the Whisper model
model = whisper.load_model("large")

# Define the function for ASR with language detection
def transcribe(audio):
    # Load audio and pad/trim it to fit 30 seconds
    audio_data = whisper.load_audio(audio)
    audio_data = whisper.pad_or_trim(audio_data)

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

    # Detect the spoken language
    _, probs = model.detect_language(mel)
    detected_language = max(probs, key=probs.get)
    
    # Decode the audio
    options = whisper.DecodingOptions()
    result = whisper.decode(model, mel, options)
    
    return f"Detected language: {detected_language}\n\nTranscription: {result.text}"

# Retain the ChatInterface setup from the existing app.py
from huggingface_hub import InferenceClient

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response

# Create the ASR interface with a label and functionality for both file upload and direct recording
asr_interface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(type="filepath", label="Upload or record audio"),
    outputs="text",
    title="ASR Transcription with Language Detection",
    description="Upload an audio file or record audio directly to get the transcription and detected language."
)

# Retain the ChatInterface setup from the existing app.py
chat_interface = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

# Combine the two interfaces into a single Gradio Blocks application
with gr.Blocks() as demo:
    gr.Markdown("# ASR and Chatbot Application")
    gr.Markdown(" ")  # Adding space between the top and the ASR interface
    asr_interface.render()
    gr.Markdown("----")
    chat_interface.render()

if __name__ == "__main__":
    demo.launch()