Downloads · 30 days
21
33% of all-time downloads
wolof
baayematar/wolof
wolof is a automatic speech recognition model from baayematar. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
64
Public
Repo size
2.5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Sep 27, 2023
- Updated
- Sep 27, 2023
- SHA
- 7ac7cde2
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
wolof
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3554
- Wer: 0.3717
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 3
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.9163 | 0.75 | 1000 | 1.0340 | 0.8431 |
| 0.77 | 1.5 | 2000 | 0.4280 | 0.5549 |
| 0.544 | 2.25 | 3000 | 0.3612 | 0.4818 |
| 0.4548 | 3.0 | 4000 | 0.3530 | 0.4606 |
| 0.3662 | 3.75 | 5000 | 0.3296 | 0.4422 |
| 0.3168 | 4.5 | 6000 | 0.3323 | 0.4303 |
| 0.2651 | 5.25 | 7000 | 0.3133 | 0.4092 |
| 0.2276 | 6.0 | 8000 | 0.3257 | 0.4073 |
| 0.1815 | 6.75 | 9000 | 0.3199 | 0.3861 |
| 0.1583 | 7.5 | 10000 | 0.3268 | 0.38 |
| 0.1313 | 8.25 | 11000 | 0.3505 | 0.3782 |
| 0.1156 | 9.0 | 12000 | 0.3571 | 0.3763 |
| 0.1032 | 9.75 | 13000 | 0.3554 | 0.3717 |
Framework versions
- Transformers 4.33.0
- Pytorch 2.0.0
- Datasets 2.1.0
- Tokenizers 0.13.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Sep 27, 2023
- Updated
- Sep 27, 2023