Downloads · 30 days
121K
11% of all-time downloads
wav2vec2-cv-be
ales/wav2vec2-cv-be
wav2vec2-cv-be is a automatic speech recognition model from ales. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as gpl-3.0.
Fine-tuned version of facebook/wav2vec2-base on mozilla-foundation/commonvoice80 be dataset.
All-time downloads
1.1M
Public
Repo size
1.6 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin534 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- gpl-3.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 13, 2022
- Updated
- Apr 13, 2022
- SHA
- 2d73dd6d
Model card
From the Hugging Face model README
Automatic Speech Recognition for Belarusian language
Fine-tuned version of facebook/wav2vec2-base on mozilla-foundation/common_voice_8_0 be dataset.
Train, Dev, Test splits were used as they are present in the dataset. No additional data was used from Validated split,
only 1 voicing of each sentence was used - the way the data was split by CommonVoice CorporaCreator.
To build a better model one can use additional voicings from Validated split for sentences already present in Train, Dev, Test splits,
i.e. enlarge mentioned splits.
Language model was built using KenLM.
5-gram Language model was built on sentences from Train + (Other - Dev - Test) splits of mozilla-foundation/common_voice_8_0 be dataset.
Source code is available here.
Run model in a browser
This page contains interactive demo widget that lets you test this model right in a browser.
However, this widget uses Acoustic model only without Language model that significantly improves overall performance.
You can play with full pipeline of Acoustic model + Language model on the following spaces page (also works from browser).
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- gpl-3.0
- Languages
- be
- Created
- Apr 13, 2022
- Updated
- Apr 13, 2022