Downloads · 30 days
9
10% of all-time downloads
ElizabethMwangi/whisper-large-v3-swahili-nss-afrivoice-5domains
whisper-large-v3-swahili-nss-afrivoice-5domains is a automatic speech recognition model from ElizabethMwangi. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Stage 2 nonstandard speech fine-tune of openai/whisper-large-v3 on the CDLI Kenyan Swahili Nonstandard Speech dataset. Built on top of ElizabethMwangi/whisper-large-v3-swahili-afrivoice-5domains, a Stage 1 checkpoint…
Downloads · 30 days
9
10% of all-time downloads
All-time downloads
86
Public
Parameters
1.5B
6.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors6.2 GB · 100%
From the Hugging Face model README
Stage 2 nonstandard speech fine-tune of openai/whisper-large-v3 on the CDLI Kenyan Swahili Nonstandard Speech dataset. Built on top of ElizabethMwangi/whisper-large-v3-swahili-afrivoice-5domains, a Stage 1 checkpoint trained on AfriVoice Swahili across all 5 domains (389,599 utterances), best step 600.
Overall, compared to unadapted baseline
| Model | Overall WER | Avg WER |
|---|---|---|
| openai/whisper-large-v3 (no adaptation) | 0.845 | - |
| Stage 1 only (afrivoice-5domains, no NSS tuning) | 0.434 | - |
| This model (adapted) | 0.329 | 0.279 |
| Metric | Value |
|---|---|
| Overall WER | 0.329 |
| Overall CER | 0.171 |
| Avg WER | 0.279 |
| Avg CER | 0.128 |
| Meaning preservation | 75.7% |
By severity
| Severity | WER | CER |
|---|---|---|
| Mild | 0.21 | 0.09 |
| Moderate | 0.25 | 0.11 |
| Severe | 0.35 | 0.16 |