GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
LyngualLabs
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
LyngualLabs
Model Tree
openai/whisper-small
Input Modalities
Output Modalities
Supported Functionality
| Metric | This model | whisper-small-yoruba (reported) |
|---|---|---|
| WER — tone-aware | 16.73% | 20.76% |
| WER — tone-insensitive | 13.86% | — |
| CER — tone-aware | 6.38% | — |
| CER — tone-insensitive | 5.10% | — |
A 5-epoch fine-tune on YECS brings whisper-small well below the previously reported Yoruba baseline.
Normalization: NFC → lowercase → strip Unicode P/S punctuation. Tone-aware keeps Yoruba tone diacritics (acute/grave/macron); tone-insensitive strips them but always keeps the phonemic under-dot (ọ, ẹ, ṣ). See the tagged model's card for the fuller note.
python
from transformers import WhisperForConditionalGeneration, WhisperProcessorimport torch, librosarepo = "LyngualLabs/yecs-asr-whisper-plain"proc = WhisperProcessor.from_pretrained(repo)model = WhisperForConditionalGeneration.from_pretrained(repo, torch_dtype=torch.bfloat16).to("cuda").eval()audio, _ = librosa.load("utterance.wav", sr=16000)feats = proc.feature_extractor(audio, sampling_rate=16000, return_tensors="pt").input_featuresids = model.generate(feats.to("cuda", torch.bfloat16),language="yoruba", task="transcribe", max_new_tokens=225)print(proc.tokenizer.batch_decode(ids, skip_special_tokens=True)[0])
openai/whisper-small · 5 epochs · lr 1e-5 · bf16 · effective batch 32 · 1×H200.yoruba, task transcribe.afroscale_ai_cmu_africa/yecs-lid, run whisper-plain.Research baseline for Yoruba–English code-switching ASR. Trained on YECS read/prompted
speech; performance may drop on far-field, noisy, or spontaneous conversational audio.
Two languages only (yo, en).
tag-injection/)Apache-2.0 (inherited from openai/whisper-small). YECS corpus terms apply to the
training data.