Spaces:
Sleeping
Sleeping
File size: 3,264 Bytes
c46a1db 84d5910 fcc6e0c c46a1db fcc6e0c 7287921 84d5910 c46a1db 7287921 84d5910 c46a1db fcc6e0c 84d5910 c46a1db 84d5910 c46a1db 84d5910 fcc6e0c 067c48c 84d5910 c46a1db 84d5910 c46a1db |
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 |
import torch
import spaces
import gradio as gr
from threading import Thread
import re
import time
import tempfile
import os
from transformers import pipeline
from transformers.pipelines.audio_utils import ffmpeg_read
from PIL import Image
from transformers import LlavaNextProcessor, LlavaNextForConditionalGeneration, TextIteratorStreamer
processor = LlavaNextProcessor.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf")
model = LlavaNextForConditionalGeneration.from_pretrained("llava-hf/llava-v1.6-mistral-7b-hf", torch_dtype=torch.float16, low_cpu_mem_usage=True)
model.to("cuda:0")
ASR_MODEL_NAME = "openai/whisper-large-v3"
ASR_BATCH_SIZE = 8
ASR_CHUNK_LENGTH_S = 30
TEMP_FILE_LIMIT_MB = 1000
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")
device = 0 if torch.cuda.is_available() else "cpu"
asr_pl = pipeline(
task="automatic-speech-recognition",
model=ASR_MODEL_NAME,
chunk_length_s=ASR_CHUNK_LENGTH_S,
device=device,
)
@spaces.GPU
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
@spaces.GPU
def transcribe(inputs, task):
if inputs is None:
raise gr.Error("No audio file submitted! Please upload or record an audio file before submitting your request.")
text = asr_pl(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
return text
demo = gr.Blocks()
transcribe_interface
"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
chat_interface = gr.ChatInterface(
respond,
title="Enlight Innovations Limited -- Demo",
description="This demo is desgined to illustrate our basic idea and feasibility in implementation.",
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)",
),
],
)
with demo:
gr.TabbedInterface([transcribe_interface, chat_interface], ["Step 1: Transcribe", "Step 2: "])
if __name__ == "__main__":
demo.queue().launch() #demo.launch() |