from transformers import Wav2Vec2ForCTC, AutoProcessor
import torch, torchaudio
processor = AutoProcessor.from_pretrained("aadel4/omniASR-CTC-300M-v2")
model     = Wav2Vec2ForCTC.from_pretrained("aadel4/omniASR-CTC-300M-v2")
model.eval()
waveform, sr = torchaudio.load("audio.wav")
if sr != 16_000:
    waveform = torchaudio.functional.resample(waveform, sr, 16_000)
inputs = processor(
    waveform.squeeze().numpy(), sampling_rate=16_000, return_tensors="pt"
)
with torch.no_grad():
    logits = model(**inputs).logits          # (1, T, vocab)
pred_ids   = torch.argmax(logits, dim=-1)
transcript = processor.decode(pred_ids[0])
print(transcript)

KevinKibe/omniASR-CTC-300M-v2

omniASR-CTC-300M-v2

Code Base

Usage

KevinKibe/
omniASR-CTC-300M-v2