# import numpy as np

import gradio as gr

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline

# from datasets import load_dataset


device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32

# model_id = "openai/whisper-small"
model_id = "openai/whisper-large-v3"

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id, torch_dtype=torch_dtype, low_cpu_mem_usage=True, use_safetensors=True
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=processor.tokenizer,
    feature_extractor=processor.feature_extractor,
    max_new_tokens=128,
    chunk_length_s=30,
    batch_size=16,
    return_timestamps=True,
    torch_dtype=torch_dtype,
    device=device,
)

# dataset = load_dataset("distil-whisper/librispeech_long", "clean", split="validation")
# sample = dataset[0]["audio"]

# result = pipe(sample)
# print(result["text"])


def reverse_audio(audio):
    # sr, data = audio
    result = pipe(audio)
    print(result["text"])
    return result


input_audio = gr.Audio(
    sources=["microphone"],
    waveform_options=gr.WaveformOptions(
        waveform_color="#01C6FF",
        waveform_progress_color="#0066B4",
        skip_length=2,
        show_controls=False,
    ),
)
demo = gr.Interface(fn=reverse_audio, inputs=input_audio, outputs="audio")

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