app.py

# import gradio as gr
# from huggingface_hub import InferenceClient

# """
# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
# """
# 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


# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = 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)",
#         ),
#     ],
# )


# if __name__ == "__main__":
#     demo.launch()
# import gradio as gr
# from faster_whisper import WhisperModel

# # Try to load the model on startup
# try:
#     model = WhisperModel("medium", device="cpu", compute_type="int8")
# except Exception as e:
#     # You could log the error or handle it more gracefully if needed
#     model = None
#     model_error = f"Failed to load model: {e}"

# def transcribe(audio_file):
#     if model is None:
#         return model_error
#     try:
#         segments, info = model.transcribe(audio_file.name, beam_size=5)
#         text = " ".join([seg.text for seg in segments])
#         return text
#     except Exception as e:
#         return f"Transcription failed: {e}"

# iface = gr.Interface(
#     fn=transcribe,
#     inputs=gr.Audio(sources=["upload"], type="filepath", label="Audio file"),
#     outputs="text",
#     title="Faster Whisper Transcription API",
#     description="Upload audio and get transcription text."
# )

# iface.launch(server_name="0.0.0.0", server_port=7860)
import gradio as gr
from faster_whisper import WhisperModel

# Try to load the model on startup
try:
    model = WhisperModel("medium", device="cpu", compute_type="int8")
except Exception as e:
    model = None
    model_error = f"Failed to load model: {e}"

def transcribe(audio_file):
    if model is None:
        return model_error
    try:
        segments, info = model.transcribe(audio_file, beam_size=5)
        text = " ".join([seg.text for seg in segments])
        return text
    except Exception as e:
        return f"Transcription failed: {e}"

iface = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources=["upload"], type="filepath", label="Audio file"),
    outputs="text",
    title="Faster Whisper Transcription API",
    description="Upload audio and get transcription text."
)

iface.launch(server_name="0.0.0.0", server_port=7880)