Downloads · 30 days
92
9% of all-time downloads
wav2vec2-bert-CV16-de
sharrnah/wav2vec2-bert-CV16-de
wav2vec2-bert-CV16-de is a automatic speech recognition model from sharrnah. Use it when you need speech turned into text. It is set up for transformers.
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the MOZILLA-FOUNDATION/COMMONVOICE160 - DE dataset. It achieves the following results on the evaluation set: - Loss: 0.095182 - Wer: 0.066672 - Steps: 250…
All-time downloads
972
Public
Parameters
606M
4.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2-bert
- Access
- Public
- Created
- Feb 9, 2024
- Updated
- Feb 11, 2024
- SHA
- 8fa911a6
Model card
From the Hugging Face model README
wav2vec2-bert-CV16-de
This model is a fine-tuned version of facebook/w2v-bert-2.0 on the MOZILLA-FOUNDATION/COMMON_VOICE_16_0 - DE dataset. It achieves the following results on the evaluation set:
- Loss: 0.095182
- Wer: 0.066672
- Steps: 25000
- epoch: 10
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2-bert
- Languages
- de
- Created
- Feb 9, 2024
- Updated
- Feb 11, 2024