import librosa

import torch
from transformers import WhisperForConditionalGeneration, WhisperProcessor

y, sr = librosa.load('audio.mp3', sr=16000)

MODEL_NAME = "alvanlii/whisper-small-cantonese"

processor = WhisperProcessor.from_pretrained(MODEL_NAME)
model = WhisperForConditionalGeneration.from_pretrained(MODEL_NAME)

processed_in = processor(y, sampling_rate=sr, return_tensors="pt")
gout = model.generate(
    input_features=processed_in.input_features, 
    output_scores=True, return_dict_in_generate=True
)
transcription = processor.batch_decode(gout.sequences, skip_special_tokens=True)[0]
print(transcription)

from transformers import pipeline
MODEL_NAME = "alvanlii/whisper-small-cantonese" 
lang = "zh"
pipe = pipeline(
    task="automatic-speech-recognition",
    model=MODEL_NAME,
    chunk_length_s=30,
    device=device,
)
pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language=lang, task="transcribe")
text = pipe(file)["text"]

model = AutoModelForSpeechSeq2Seq.from_pretrained(
    "alvanlii/whisper-small-cantonese",
    torch_dtype=torch_dtype,
    low_cpu_mem_usage=True,
    use_safetensors=True,
    attn_implementation="sdpa",
)

model_id = "simonl0909/whisper-large-v2-cantonese"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
    model_id,
    torch_dtype=torch_dtype,
    low_cpu_mem_usage=True,
    use_safetensors=True,
    attn_implementation="sdpa",
)
model.to(device)

processor = AutoProcessor.from_pretrained(model_id)

assistant_model_id = "alvanlii/whisper-small-cantonese"

assistant_model = AutoModelForSpeechSeq2Seq.from_pretrained(
    assistant_model_id,
    torch_dtype=torch_dtype,
    low_cpu_mem_usage=True,
    use_safetensors=True,
    attn_implementation="sdpa",
)

assistant_model.to(device)
...
model.generate(**inputs, use_cache=True, assistant_model=assistant_model)