GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Haramiday
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
Haramiday
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
| Test set | Metric | This model | Base model (zero-shot) |
|---|---|---|---|
| Òwe-Voice proverbs, 3 unseen speakers (750 utt.) | WER | 0.353 [0.338, 0.369] | 1.012 |
| CER | 0.118 | 0.572 | |
| WER ignoring all diacritics | 0.263 | 0.873 | |
| Tone error rate (on correctly recognised vowels) | 0.108 | 0.699 | |
| FLEURS Yorùbá test (conventional read speech) | WER | 0.794 | 1.014 |
Seed variability on the proverb test set: single seed.
Scoring. References and hypotheses are normalised identically: Unicode NFC, lower-casing, removal of
.,!?;:"“”‘’()[]/\, whitespace collapsed; tone marks and underdots are kept. WER/CER are corpus-level (total
edits / total reference units) with 95% bootstrap confidence intervals over utterances. FLEURS = Yorùbá (yo_ng) test set,
817 utterances ≤ 30 s.
python
import torch, librosafrom transformers import WhisperProcessor, WhisperForConditionalGenerationproc = WhisperProcessor.from_pretrained("Haramiday/owe-voice-whisper-large-v3-yoruba", language="yoruba", task="transcribe")model = WhisperForConditionalGeneration.from_pretrained("Haramiday/owe-voice-whisper-large-v3-yoruba").eval()audio, _ = librosa.load("proverb.wav", sr=16000)features = proc.feature_extractor(audio, sampling_rate=16000, return_tensors="pt").input_featureswith torch.no_grad(): ids = model.generate(features, language="yoruba", task="transcribe")print(proc.tokenizer.batch_decode(ids, skip_special_tokens=True)[0]) # Convenience alternative (decoding can differ slightly from the reported numbers):# from transformers import pipeline# asr = pipeline("automatic-speech-recognition", model="Haramiday/owe-voice-whisper-large-v3-yoruba")# asr("proverb.wav", generate_kwargs={"language": "yoruba", "task": "transcribe"})Audio must be 16 kHz mono.
Training data. Òwe-Voice (Abolade, 2026): read Yorùbá proverbs recorded in a studio by 12 volunteer native speakers. The corpus is not publicly released; access is at the discretion of its creators. Fine-tuning used a speaker-disjoint split: 8 speakers / 3,996 utterances / 5.17 h for training, 1 speaker / 250 utterances for checkpoint selection (dev), and 3 unseen speakers / 750 utterances / 0.95 h for testing. Each proverb was read exactly once.
Procedure. Full fine-tuning, learning rate 1e-5, linear warm-up 200 steps, batch size 16, fp16, gradient checkpointing, up to 10 epochs; the checkpoint with the lowest dev WER is kept. Language and task fixed to Yorùbá transcription. Seed 42.
Hardware: 1 × NVIDIA H200. Software: transformers 4.57.1, torch 2.8.
bibtex
@inproceedings{owevoice2026speech, title = {Evaluating and Fine-Tuning Speech Technologies on Culturally Grounded Yor\`ub\'a Proverbs Using the \`Owe-Voice Proverb Speech Corpus}, author = {Fagoroye, Ayomide Emmanuel and Odumuyiwa, Victor and Abolade, Daud and Ola-obaado, Similoluwa and Taiwo, Iyanda}, booktitle = {Africa in AI Affinity Group at Neural Information Processing Systems (NeurIPS)}, year = {2026}}import torch, librosafrom transformers import WhisperProcessor, WhisperForConditionalGenerationproc = WhisperProcessor.from_pretrained("Haramiday/owe-voice-whisper-large-v3-yoruba", language="yoruba", task="transcribe")model = WhisperForConditionalGeneration.from_pretrained("Haramiday/owe-voice-whisper-large-v3-yoruba").eval()audio, _ = librosa.load("proverb.wav", sr=16000)features = proc.feature_extractor(audio, sampling_rate=16000, return_tensors="pt").input_featureswith torch.no_grad(): ids = model.generate(features, language="yoruba", task="transcribe")print(proc.tokenizer.batch_decode(ids, skip_special_tokens=True)[0]) # Convenience alternative (decoding can differ slightly from the reported numbers):# from transformers import pipeline# asr = pipeline("automatic-speech-recognition", model="Haramiday/owe-voice-whisper-large-v3-yoruba")# asr("proverb.wav", generate_kwargs={"language": "yoruba", "task": "transcribe"})@inproceedings{owevoice2026speech, title = {Evaluating and Fine-Tuning Speech Technologies on Culturally Grounded Yor\`ub\'a Proverbs Using the \`Owe-Voice Proverb Speech Corpus}, author = {Fagoroye, Ayomide Emmanuel and Odumuyiwa, Victor and Abolade, Daud and Ola-obaado, Similoluwa and Taiwo, Iyanda}, booktitle = {Africa in AI Affinity Group at Neural Information Processing Systems (NeurIPS)}, year = {2026}}