bosonai/higgs-audio-v3-stt download history
bosonai/higgs-audio-v3-stt is a 2.7B-parameter automatic speech recognition model by bosonai. In the last 30 days it was downloaded 10,807 times (5,344 in the last 7 days), and 24,084 times in total.
It ranks #8,121 on the Hub by monthly downloads and #349 among automatic speech recognition models.
It has 43 likes.
4 models build on higgs-audio-v3-stt: 3 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 12,276 times in the last 30 days. See the higgs-audio-v3-stt galaxy.
Most downloaded derivatives
- cstr/higgs-audio-v3-stt-GGUF (quantized), 549 downloads in 30 days
- prithivMLmods/higgs-audio-v3-stt-GGUF (quantized), 461 downloads in 30 days
- ggml-org/higgs-audio-v3-stt-GGUF (quantized), 420 downloads in 30 days
- bosonai/higgs-audio-v3-stt-v2 (finetune), 39 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 10,807 | +337% |
| October 2026 | 2,473 | +140% |
| September 2026 | 1,030 | +2% |
| August 2026 | 1,010 | -86% |
| July 2026 | 7,105 | +168% |
| June 2026 | 2,648 | +2053% |
| May 2026 | 123 | -71% |
| April 2026 | 421 | +192% |
Its busiest 30 days so far ended on 2026-11-18, with 10,807 downloads.
Open bosonai/higgs-audio-v3-stt on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.