from transformers import (
    AutomaticSpeechRecognitionPipeline,
    WhisperForConditionalGeneration,
    WhisperTokenizer,
    WhisperProcessor,
)
from peft import PeftModel, PeftConfig
import torch
from huggingface_hub import snapshot_download, login

login()

peft_model_id = "aisha-org/faster-whisper-uz"
language = "uz"
task = "transcribe"

peft_config = PeftConfig.from_pretrained(peft_model_id, use_auth_token=True)

model = WhisperForConditionalGeneration.from_pretrained(
    peft_config.base_model_name_or_path, 
    load_in_8bit=True, 
    device_map="auto",
    use_auth_token=True,
    force_download=True,
    resume_download=False
)

model = PeftModel.from_pretrained(model, peft_model_id, use_auth_token=True)

tokenizer = WhisperTokenizer.from_pretrained(peft_config.base_model_name_or_path, language=language, task=task)
processor = WhisperProcessor.from_pretrained(peft_config.base_model_name_or_path, language=language, task=task)
feature_extractor = processor.feature_extractor
forced_decoder_ids = processor.get_decoder_prompt_ids(language=language, task=task)

pipe = AutomaticSpeechRecognitionPipeline(model=model, tokenizer=tokenizer, feature_extractor=feature_extractor)
def transcribe(audio):
    with torch.cuda.amp.autocast():
        text = pipe(audio, generate_kwargs={"forced_decoder_ids": forced_decoder_ids}, max_new_tokens=255)["text"]
    return text
import gradio as gr

demo = gr.Blocks()

mic_transcribe = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="microphone", type="filepath"),
    outputs=gr.Textbox(),
)

file_transcribe = gr.Interface(
    fn=transcribe,
    inputs=gr.Audio(sources="upload", type="filepath"),
    outputs=gr.Textbox(),
)
with demo:
    gr.TabbedInterface(
        [mic_transcribe, file_transcribe],
        ["Transcribe Microphone", "Transcribe Audio File"],
    )

demo.launch(debug=True)