Downloads · 30 days
143
3% of all-time downloads
wav2vec2-base-it-latin
lsb/wav2vec2-base-it-latin
wav2vec2-base-it-latin is a automatic speech recognition model from lsb. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as agpl-3.0.
All-time downloads
4.2K
Public
Repo size
7.7 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- agpl-3.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022
- SHA
- 95792abd
Model card
From the Hugging Face model README
wav2vec2-base-it-latin
This model is a fine-tuned version of wav2vec2-base-it-voxpopuli
The dataset used is the poetaexmachina-mp3-recitations, all of the 2-series texts (vergil) and every tenth 1-series text (words from Poeta Ex Machina's database of words with scansions).
It achieves the following results on the evaluation set:
- Loss: 0.1943
- WER: 0.398
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- agpl-3.0
- Languages
- la
- Created
- Mar 2, 2022
- Updated
- Mar 24, 2022