Downloads · 30 days
82
23% of all-time downloads
w2v2-lg-xls-r-300m-tsonga
misterkissi/w2v2-lg-xls-r-300m-tsonga
w2v2-lg-xls-r-300m-tsonga is a automatic speech recognition model from misterkissi. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as cc-by-nc-sa-4.0.
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m. It achieves the following results on the evaluation set: - evalloss: 0.09790 - evalwer: 0.05920 - evalruntime: 397.1749 - evalsamplespersecond: 22.62…
All-time downloads
355
Public
Parameters
315M
141 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- cc-by-nc-sa-4.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jul 23, 2025
- Updated
- Aug 15, 2025
- SHA
- 42fd46fe
Base models
Model card
From the Hugging Face model README
w2v2-lg-xls-r-300m-tsonga
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m.
It achieves the following results on the evaluation set:
- eval_loss: 0.09790
- eval_wer: 0.05920
- eval_runtime: 397.1749
- eval_samples_per_second: 22.622
- eval_steps_per_second: 2.83
- epoch: 27.97668
- step: 61800
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- cc-by-nc-sa-4.0
- Created
- Jul 23, 2025
- Updated
- Aug 15, 2025