Downloads · 30 days
0
Qwen3-ASR-O.6B-Yoruba
David-A-Amoo/Qwen3-ASR-O.6B-Yoruba
Qwen3-ASR-O.6B-Yoruba is a automatic speech recognition model from David-A-Amoo. Use it when you need speech turned into text. The card lists the license as cc-by-nc-sa-4.0.
This model is a fine-tuned version of Qwen/Qwen3-ASR-0.6B trained on 85.49 hours of Yoruba speech from a cleaned version of the NaijaVoices dataset.
Access
Public
Updated Feb 15, 2026
Repo size
1.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors1.6 GB · 99%
At a glance
- Task
- Automatic Speech Recognition
- License
- cc-by-nc-sa-4.0
- Access
- Public
- Created
- Feb 15, 2026
- Updated
- Feb 15, 2026
- SHA
- 89556ce7
Base models
Model card
From the Hugging Face model README
Qwen3-ASR Fine-Tuned on Yoruba
This model is a fine-tuned version of Qwen/Qwen3-ASR-0.6B trained on 85.49 hours of Yoruba speech from a cleaned version of the NaijaVoices dataset.
Currently, only evaluation/testing checkpoints are available. Works extremely well for some samples, fails for others, good for short clips
Usage
import torch
from qwen_asr import Qwen3ASRModel
model = Qwen3ASRModel.from_pretrained("David-A-Amoo/qwen3-asr-yoruba")
results = model.transcribe(audio="audio.wav")
print(results[0].language)
print(results[0].text)
cc-by-nc-sa-4.0 license inheriting naijavoices dataset licensing.
- Task
- Automatic Speech Recognition
- License
- cc-by-nc-sa-4.0
- Languages
- yo
- Created
- Feb 15, 2026
- Updated
- Feb 15, 2026