whisper-base vs wav2vec2-xls-r-300m-ftspeech
Specs, VRAM requirements and download trends — updated 28 July 2026.
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | whisper-base | wav2vec2-xls-r-300m-ftspeech |
|---|---|---|
| Parameters | 70 M | 320 M |
| Architecture | WhisperForConditionalGeneration | Wav2Vec2ForCTC |
| Context length | — | — |
| Licence | apache-2.0 | other |
| Commercial use | Allowed | Unknown |
| Languages | 99 | 1 |
| Downloads 30d | 4,759,784 | 511,855 |
| Downloads all time | 46.7 M | 11.4 M |
| Quantizations on the Hub | SAFETENSORS | SAFETENSORS |
| Gated | No | No |
| First seen on the Hub | 2022-09-26 | 2022-03-04 |
Download trend
Daily snapshots, last 10 days (28 Jul – 6 Aug)
6.4 M434 K
whisper-base
wav2vec2-xls-r-300m-ftspeech
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
whisper-base · fp16
0.8 GB / 24 GB
wav2vec2-xls-r-300m-ftspeech · fp16
1.9 GB / 24 GB