Pirnazar/whisper-large-v3-turbo-turkmen-lora

pip install "transformers==5.17.0" "peft==0.21.0" torch soundfile scipy

import math
import torch
import soundfile as sf
from scipy.signal import resample_poly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
from peft import PeftModel

repo = "Pirnazar/whisper-large-v3-turbo-turkmen-lora"
device = "cuda" if torch.cuda.is_available() else "cpu"
dtype = torch.float16 if device == "cuda" else torch.float32
processor = AutoProcessor.from_pretrained(repo)
base = AutoModelForSpeechSeq2Seq.from_pretrained(
    "openai/whisper-large-v3-turbo", dtype=dtype,
)
model = PeftModel.from_pretrained(base, repo).merge_and_unload().to(device).eval()
audio, sr = sf.read("audio.wav", dtype="float32")
if audio.ndim == 2:
    audio = audio.mean(axis=1)
if sr != 16000:
    divisor = math.gcd(sr, 16000)
    audio = resample_poly(audio, 16000 // divisor, sr // divisor)
if len(audio) > 30 * 16000:
    raise ValueError("Split recordings into clips of at most 30 seconds for this example.")
inputs = processor(audio, sampling_rate=16000, return_tensors="pt", return_attention_mask=True)
model.generation_config.forced_decoder_ids = None
with torch.inference_mode():
    ids = model.generate(
        inputs.input_features.to(device=device, dtype=dtype),
        attention_mask=inputs.attention_mask.to(device),
        language="tk", task="transcribe", return_timestamps=False,
    )
print(processor.batch_decode(ids, skip_special_tokens=True)[0])