Spaces:
Runtime error
Runtime error
File size: 3,664 Bytes
89f28ce f058c5e 39e2b3a 89f28ce a535c7a 39e2b3a 89f28ce a535c7a f058c5e a535c7a 89f28ce e303ba8 89f28ce 39e2b3a f058c5e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 |
# 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)
|