import streamlit as st
from transformers import AutoProcessor, BarkModel, AutoModelForSpeechSeq2Seq, pipeline
from datasets import load_dataset
import torch
import scipy

st.title('Suno bark - text to speech and Whisper audio to translation')

text_input = st.text_input(
    "Enter some text 👇",
    max_chars=400
)

if text_input:
    st.write("You entered: ", text_input)


if st.button('Generate and play'):
    processor = AutoProcessor.from_pretrained("suno/bark")
    model = BarkModel.from_pretrained("suno/bark")

    voice_preset = "v2/en_speaker_6"
    print("input", text_input)
    inputs = processor(text_input, voice_preset=voice_preset)

    audio_array = model.generate(**inputs)
    audio_array = audio_array.cpu().numpy().squeeze()
    sample_rate = model.generation_config.sample_rate

    some_file_path = 'bark_out.wav'
    scipy.io.wavfile.write(some_file_path, rate=sample_rate, data=audio_array)

    st.audio(some_file_path, format="audio/wav", loop=False)


uploaded_file = st.file_uploader("Choose a file")
bytes_data = None
if uploaded_file is not None:
    # To read file as bytes:
    bytes_data = uploaded_file.getvalue()

if st.button('Generate and translate'):
    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-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 = bytes_data

    result = pipe(sample, generate_kwargs={"task": "translate"})
    print(result["text"])
    st.write(result["text"])