Downloads · 30 days
3
1% of all-time downloads
xlsr-wav2vec2-final-1-lm-3
chrisvinsen/xlsr-wav2vec2-final-1-lm-3
xlsr-wav2vec2-final-1-lm-3 is a automatic speech recognition model from chrisvinsen. Use it when you need speech turned into text. It is set up for transformers.
Indonli + CommonVoice8.0 Dataset -- Train + Validation + Test
All-time downloads
415
Public
Repo size
2.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 97%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- May 29, 2022
- Updated
- Jun 2, 2022
- SHA
- 38e356aa
Model card
From the Hugging Face model README
Indonli + CommonVoice8.0 Dataset --> Train + Validation + Test
WER : 0.216
WER with LM: 0.104
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- May 29, 2022
- Updated
- Jun 2, 2022