import gradio as gr
import numpy as np
from transformers import WhisperProcessor, WhisperForConditionalGeneration
import librosa

processor = WhisperProcessor.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
model = WhisperForConditionalGeneration.from_pretrained("Neurai/NeuraSpeech_WhisperBase")
forced_decoder_ids = processor.get_decoder_prompt_ids(language="fa", task="transcribe")


def transcribe(audio):
    if audio is None:
        return "No audio input provided. Please record or upload an audio file."

    array, sample_rate = librosa.load(audio)
    array = array.astype(np.float32)
    sr = 16000
    array = librosa.to_mono(array)
    array = librosa.resample(array, orig_sr=sample_rate, target_sr=sr)
    input_features = processor(array, sampling_rate=sr, return_tensors="pt").input_features

    predicted_ids = model.generate(input_features)
    transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
    return transcription[0]


demo = gr.Interface(
    fn=transcribe,
    inputs=[gr.Audio(sources=["microphone"], type='filepath')],
    outputs="text",
    allow_flagging="never",
)

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