Model reference · open weights
whisper-small-Swahili_finetuned_small_CV20 is an open-weight audio or speech model from cdli. whisper-small-Swahili_finetuned_small_CV20 (FP32) weighs 483 MB; the smallest configuration that runs it is RTX 3060 12 GB.
What it is
| Released by | cdli |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 242M |
| Runs with | transformers |
| Released | 2025-08-22 |
| Popularity | 653 downloads / month |
| Weights | 483 MB (whisper-small-Swahili_finetuned_small_CV20 (FP32), file size) |
| Licence | Licence not stated |
What it runs on
Weights 483 MB (file size) · overhead about 1.6 GB.
| Card | One stream | Counted memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
Estimates, not measurements: the weights are the build's file size. A speech model's decoder keeps a small cache for every stream it transcribes, so memory grows with the streams and beams at once. Counted memory is 92 % of what CUDA reports for the card.
From the model card
trained on: cdli/common_voice_swahili_small
performance (WER):
Quoted from the model card on Hugging Face — the full card is behind the Hugging Face link above.