facebook/data2vec-audio-base-960h download history
facebook/data2vec-audio-base-960h is an automatic speech recognition model by facebook. In the last 30 days it was downloaded 10,471 times (1,959 in the last 7 days), and 457,725 times in total.
It ranks #7,978 on the Hub by monthly downloads and #314 among automatic speech recognition models.
It has 12 likes.
6 models build on data2vec-audio-base-960h: 2 quantized, 4 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 11,498 times in the last 30 days. See the data2vec-audio-base-960h galaxy.
Most downloaded derivatives
- cstr/data2vec-audio-960h-GGUF (quantized), 983 downloads in 30 days
- loom-ai-org/data2vec-audio-base-960h-loom (quantized), 18 downloads in 30 days
- jjyaoao/Echotune_clean_test (finetune), 15 downloads in 30 days
- None58/my_awesome_asr_mind_model3 (finetune), 4 downloads in 30 days
- bASILgIL/wav2vec_5e-5_3 (finetune), 4 downloads in 30 days
- FarziBuilder/my_awesome_asr_mind_model (finetune), 3 downloads in 30 days