Downloads · 30 days
4
4% of all-time downloads
whisper-small-ha
nahomazmach/whisper-small-ha
whisper-small-ha is a automatic speech recognition model from nahomazmach. Use it when you need speech turned into text. The card lists the license as apache-2.0.
openai/whisper-small fine-tuned for Hausa automatic speech recognition on the hang config of google/fleurs (3259 train / 621 test clips), 3 epochs.
All-time downloads
114
Public
Parameters
242M
967 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026
- SHA
- c4e2b47d
Base models
Datasets
Model card
From the Hugging Face model README
whisper-small-ha
openai/whisper-small fine-tuned for Hausa automatic speech recognition on the
ha_ng config of google/fleurs
(3259 train / 621 test clips), 3 epochs.
Test set WER: 44.68% (eval_loss: 0.712)
Usage
from transformers import WhisperForConditionalGeneration, WhisperProcessor
processor = WhisperProcessor.from_pretrained("nahomazmach/whisper-small-ha")
model = WhisperForConditionalGeneration.from_pretrained("nahomazmach/whisper-small-ha")
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- ha
- Created
- Aug 5, 2026
- Updated
- Aug 5, 2026