kyrgyz-whisper-medium

import torch
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline, WhisperFeatureExtractor, AutoTokenizer

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

model_id = "nineninesix/kyrgyz-whisper-medium"

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

feature_extractor = WhisperFeatureExtractor.from_pretrained(model_id)

tokenizer = AutoTokenizer.from_pretrained(
    model_id,
    trust_remote_code=True, language="kyrgyz", task="transcribe")

pipe = pipeline(
    "automatic-speech-recognition",
    model=model,
    tokenizer=tokenizer,
    feature_extractor=feature_extractor,
    torch_dtype=torch_dtype,
    device=device
)

result = pipe("audio.mp3")
print(result['text'])