Downloads · 30 days
5
19% of all-time downloads
loso_main_M01
Theju/loso_main_M01
loso_main_M01 is a automatic speech recognition model from Theju. 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
26
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
- Feb 23, 2023
- Updated
- Feb 23, 2023
- SHA
- 14cf3500
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. -->
loso_main_M01
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: 0.0591
- Wer: 1.5385
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: 8
- 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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 8.9127 | 0.93 | 500 | 3.6520 | 1.0 |
| 2.7559 | 1.86 | 1000 | 1.7221 | 2.2189 |
| 1.0787 | 2.79 | 1500 | 0.2989 | 2.0394 |
| 0.3145 | 3.72 | 2000 | 0.1794 | 1.6923 |
| 0.1552 | 4.66 | 2500 | 0.0671 | 1.5168 |
| 0.0797 | 5.59 | 3000 | 0.0635 | 1.4951 |
| 0.0423 | 6.52 | 3500 | 0.0591 | 1.5385 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Feb 23, 2023
- Updated
- Feb 23, 2023