pyannote/speaker-diarization-3.1 download history
pyannote/speaker-diarization-3.1 is an automatic speech recognition model by pyannote. In the last 30 days it was downloaded 7,165,745 times (1,679,510 in the last 7 days), and 350,778,661 times in total.
It ranks #52 on the Hub by monthly downloads and #3 among automatic speech recognition models.
It has 4,079 likes, 165 of them in the last week.
39 models build on speaker-diarization-3.1: 1 quantized, 37 fine-tuned, 0 adapters and 1 merges. Together with the original they were downloaded 7,166,779 times in the last 30 days. See the speaker-diarization-3.1 galaxy.
Most downloaded derivatives
- litert-community/Speaker-Diarization-LiteRT (quantized), 233 downloads in 30 days
- JSWOOK/pyannote_3_fine_tuning (finetune), 59 downloads in 30 days
- Akchunks/speaker-segmentation-fine-tuned-hindi (finetune), 44 downloads in 30 days
- shreyaskal3/speaker-segmentation-fine-tuned-hindi (finetune), 38 downloads in 30 days
- Sam3000/OUTPUT_DIR (finetune), 30 downloads in 30 days
- whitneyten/whitneyTest (finetune), 30 downloads in 30 days
- urs-rs/speaker-segmentation-fine-tuned-hindi (finetune), 29 downloads in 30 days
- whitneyten/pydiarize-synthetic-japan (finetune), 29 downloads in 30 days
- Sam3000/bangla-segment (finetune), 28 downloads in 30 days
- jamil117/speaker-segmentation-fine-tuned-callhome-jpn (finetune), 28 downloads in 30 days
- ghxjiks/ppnul_ft (finetune), 25 downloads in 30 days
- whitneyten/pydiarize-Dataset-2_4-update_01 (finetune), 25 downloads in 30 days