import os
import torch
from transformers import pipeline
from transformers.pipelines.audio_utils import ffmpeg_read
import gradio as gr

MODEL_NAME = "CGIAR/chichewa-asr"
BATCH_SIZE = 8

device = 0 if torch.cuda.is_available() else "cpu"

pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
    token=os.getenv('HF_TOKEN'),
)

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 = pipe(inputs, batch_size=BATCH_SIZE, generate_kwargs={"task": task}, return_timestamps=True)["text"]
    return  text

demo = gr.Blocks()

mic_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.Audio(sources="microphone", type="filepath"),
        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
    ],
    outputs="text",
    # layout="horizontal",
    theme="huggingface",
    title="Chichewa Whisper Demo: Transcribe Audio",
    description=(
        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
        " of arbitrary length."
    ),
    allow_flagging="never",
)

file_transcribe = gr.Interface(
    fn=transcribe,
    inputs=[
        gr.Audio(sources="upload", label="Audio file", type="filepath"),
        gr.Radio(["transcribe", "translate"], label="Task", value="transcribe"),
    ],
    outputs="text",
    # layout="horizontal",
    theme="huggingface",
    title="Chichewa Whisper Demo: Transcribe Audio",
    description=(
        "Transcribe long-form microphone or audio inputs with the click of a button! Demo uses the"
        f" checkpoint [{MODEL_NAME}](https://huggingface.co/{MODEL_NAME}) and 🤗 Transformers to transcribe audio files"
        " of arbitrary length."
    ),
    examples=[
        ["./221111-214633_nya_626_elicit_7.wav", "transcribe"],
        ["./221112-004306_nya_626_elicit_9.wav", "transcribe"],
        ["./221111-214633_nya_626_elicit_25.wav", "transcribe"],
        ["./221111-214633_nya_626_elicit_45.wav", "transcribe"],
    ],
    cache_examples=True,
    allow_flagging="never",
)

with demo:
    gr.TabbedInterface([mic_transcribe, file_transcribe], ["Transcribe Microphone", "Transcribe Audio File"])

demo.queue(max_size=10)
demo.launch()