Wav2Vec 2.0 models
32 Wav2Vec 2.0 models on Hugging Face, from 315M to 963M parameters. At the precision each one is published in, the smallest needs about 1.4 GB of VRAM (wav2vec2-large-xlsr-53-basque, cheapest live fit: V100) and the largest about 4.3 GB (nb-wav2vec2-1b-bokmaal-v2, cheapest live fit: V100). The cheapest way to run wav2vec2-large-xlsr-53-basque is $0.088/hr.
Wav2Vec 2.0 models
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
