| Model | HF Name | Creator | Task | Library | Dataset | Language | Paper | Related to | License |
|---|
| Fine-tuned XLSR-53 large for speech recognition in English model | jonatasgrosman/wav2vec2-large-xlsr-53-english | Jonatasgrosman | Automatic Speech Recognition | PyTorch
JAX
Transformers | Common voice
Mozilla-foundation/common voice 6 0 | English | | Audio
Wav2vec2
Speech
Hf-asr-leaderboard
Mozilla-foundation/common voice 6 0
Robust-speech-event
Xlsr-fine-tuning-week | Apache-2.0 |
| Fine-tuned XLSR-53 large for speech recognition in Japanese model | jonatasgrosman/wav2vec2-large-xlsr-53-japanese | Jonatasgrosman | Automatic Speech Recognition | PyTorch
JAX
Transformers | Common voice | Japanese | | Audio
Wav2vec2
Speech
Xlsr-fine-tuning-week | Apache-2.0 |
| HuBERT-Base for Emotion Recognition model | superb/hubert-base-superb-er | Superb | Audio Classification | PyTorch
Transformers | Superb | English | 2105.01051 | Audio
Speech
Hubert | Apache-2.0 |
| Segmentation model | pyannote/segmentation | Pyannote | Voice Activity Detection | PyTorch
Pyannote.audio | Ami
Dihard
Voxconverse | | 2104.04045 | Audio
Speech
Speaker
Pyannote
Pyannote-audio-model
Voice
Speaker-segmentation
Overlapped-speech-detection
Resegmentation | Mit |
| Speaker Verification with ECAPA-TDNN embeddings on Voxceleb model | speechbrain/spkrec-ecapa-voxceleb | Speechbrain | | PyTorch
Speechbrain | Voxceleb | English | 2106.04624 | Embeddings
Speaker
Verification
Identification
ECAPA
TDNN | Apache-2.0 |
| Speaker embedding model | pyannote/embedding | Pyannote | | PyTorch
TensorBoard
Pyannote.audio | Voxceleb | | | Audio
Speech
Speaker
Pyannote
Pyannote-audio-model
Voice
Speaker-recognition
Speaker-verification
Speaker-identification
Speaker-embedding | Mit |
| Speaker-diarization model | pyannote/speaker-diarization | Pyannote | Automatic Speech Recognition
Voice Activity Detection | Pyannote.audio | Voxceleb
Ami
Dihard
Voxconverse
Aishell
Repere | | 2012.01477
2110.07058
2005.08072 | Audio
Speech
Speaker
Pyannote
Voice
Overlapped-speech-detection
Pyannote-audio-pipeline
Speaker-diarization
Speaker-change-detection | Mit |
| Wav2Vec2-Base model | facebook/wav2vec2-base | Meta | | PyTorch
Transformers | Librispeech asr | English | 2006.11477 | Wav2vec2
Speech
Pretraining | Apache-2.0 |
| Wav2Vec2-Base-960h model | facebook/wav2vec2-base-960h | Meta | Automatic Speech Recognition | PyTorch
TensorFlow
Safetensors
Transformers | Librispeech asr | English | 2006.11477 | Audio
Wav2vec2
Hf-asr-leaderboard | Apache-2.0 |
| Wav2Vec2-Large-960h model | facebook/wav2vec2-large-960h | Meta | Automatic Speech Recognition | PyTorch
Transformers | Librispeech asr | English | 2006.11477 | Wav2vec2
Speech | Apache-2.0 |
| Wav2Vec2-Large-960h-Lv60 Self-Training model | facebook/wav2vec2-large-960h-lv60-self | Meta | Automatic Speech Recognition | PyTorch
TensorFlow
JAX
Transformers | Librispeech asr | English | 2010.11430
2006.11477 | Audio
Wav2vec2
Speech
Hf-asr-leaderboard | Apache-2.0 |
| Wav2Vec2-Large-XLSR-53 finetuned on multi-lingual Common Voice model | facebook/wav2vec2-xlsr-53-espeak-cv-ft | Meta | Automatic Speech Recognition | PyTorch
Transformers | Common voice | Multi-lingual | 2109.11680 | Audio
Wav2vec2
Speech
Phoneme-recognition | Apache-2.0 |
| Wav2Vec2-large-a model | yongjian/wav2vec2-large-a | Yongjian | Automatic Speech Recognition | PyTorch
Transformers | LIUM/tedlium | English | | Audio
Wav2vec2
Speech | |
| Wave2Vec2-large-robust-ft-libritts-voxpopuli model | jbetker/wav2vec2-large-robust-ft-libritts-voxpopuli | Jbetker | Automatic Speech Recognition | PyTorch
Transformers | | | | Wav2vec2 | |
| Whisper large v2 model | openai/whisper-large-v2 | Openai | Automatic Speech Recognition | PyTorch
TensorFlow
Transformers | | 99 languages | 2212.04356 | Audio
Hf-asr-leaderboard
Whisper | Apache-2.0 |
