Downloads · 30 days
3
1% of all-time downloads
xlsr-wav2vec2-final-1-lm-1
chrisvinsen/xlsr-wav2vec2-final-1-lm-1
xlsr-wav2vec2-final-1-lm-1 is a automatic speech recognition model from chrisvinsen. Use it when you need speech turned into text. It is set up for transformers.
CommonVoice Dataset 8.0 -- Train + Test + Validation
All-time downloads
362
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- May 27, 2022
- Updated
- May 29, 2022
- SHA
- 251b3d83
Model card
From the Hugging Face model README
CommonVoice Dataset 8.0 --> Train + Test + Validation
WER : 0.216
WER with LM: 0.123
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- May 27, 2022
- Updated
- May 29, 2022