Modelpublic

csikasote/omniASR-CTC-300M-v2-Zulu-All-v2

sourceHugging Faceupdated 1mo agoView on Hugging Face

0likes8downloads

Model Card

omniASR-CTC-300M-v2-Zulu-All-v2

Wav2Vec2 CTC ASR model (v2) converted from the OmniLingual fairseq2 checkpoint omniASR_CTC_300M_v2.

This model outputs CTC logits over a SentencePiece vocabulary and can transcribe speech in multiple languages.

Model details

Property	Value
HF class	`Wav2Vec2ForCTC`
Encoder layers	24
Hidden size	1024
Attention heads	16
FFN intermediate	4096
Vocabulary size	10288
Source framework	fairseq2
Source card	`omniASR_CTC_300M_v2`
Parity verification	✅ Verified

Numerical parity against the original fairseq2 checkpoint has been confirmed: outputs match to within atol=1e-4 on a held-out audio sample.

Usage

python

from transformers import Wav2Vec2ForCTC, AutoProcessor
import torch, torchaudio

processor = AutoProcessor.from_pretrained("omniASR-CTC-300M-v2-Zulu-All-v2")
model     = Wav2Vec2ForCTC.from_pretrained("omniASR-CTC-300M-v2-Zulu-All-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)