openslr/librispeech_asr download history
openslr/librispeech_asr is an automatic speech recognition dataset on the Hugging Face Hub. In the last 30 days it was downloaded 52,359 times (15,187 in the last 7 days), and 1,911,554 times in total. It ranks #482 among datasets by monthly downloads.
Dataset Card for librispeech_asr Dataset Summary LibriSpeech is a corpus of approximately 1000 hours of 16kHz read English speech, prepared by Vassil Panayotov with the assistance of Daniel Povey. The data is derived from read audiobooks from the LibriVox project, and has been
Models trained on librispeech_asr
123 models list it as training data.
- Simon-Kotchou/ssast-small-patch-audioset-16-16 955 downloads in 30 days
- hf-audio/xcodec-hubert-librispeech 802 downloads in 30 days
- KrorngAI/TrorYongASR-small 701 downloads in 30 days
- aiola/whisper-medusa-linear-libri 596 downloads in 30 days
- OpenMOSS-Team/MOSS-Transcribe-preview-2B 465 downloads in 30 days
- Simon-Kotchou/ssast-base-patch-audioset-16-16 357 downloads in 30 days
- KrorngAI/TrorYongASR-tiny 306 downloads in 30 days
- mradermacher/salt-qwen2.5-0.5b-asr-tts-GGUF 292 downloads in 30 days
- Lwasinam/voicera 251 downloads in 30 days
- TigreGotico/wakehubert-tiny 246 downloads in 30 days
- aiola/whisper-medusa-block-libri 220 downloads in 30 days
- q-project/Q-Omni-53M-Experimental 156 downloads in 30 days
Spaces using librispeech_asr
- Model Pulse 8 likes
- BenchHub Leaderboards 8 likes
- Toprak1yu/voice-turn-taking-detector 0 likes