Downloads · 30 days
6
40% of all-time downloads
xlsr53-coraa-2
lejonck/xlsr53-coraa-2
xlsr53-coraa-2 is a automatic speech recognition model from lejonck. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
15
Public
Parameters
315M
1.3 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
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 25, 2025
- Updated
- Aug 25, 2025
- SHA
- 67011b6d
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. -->
xlsr53-coraa-2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1755
- Wer: 0.4003
- Cer: 0.1804
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 1.5566 | 1.0 | 3000 | 1.1274 | 0.4251 | 0.1955 |
| 1.02 | 2.0 | 6000 | 1.1293 | 0.4247 | 0.1925 |
| 1.4261 | 3.0 | 9000 | 1.1418 | 0.4299 | 0.1946 |
| 1.0087 | 4.0 | 12000 | 1.0708 | 0.4238 | 0.1881 |
| 1.9648 | 5.0 | 15000 | 1.1212 | 0.4173 | 0.1870 |
| 1.2052 | 6.0 | 18000 | 1.1291 | 0.4158 | 0.1857 |
| 1.1325 | 7.0 | 21000 | 1.1334 | 0.4084 | 0.1836 |
| 0.7304 | 8.0 | 24000 | 1.1657 | 0.4077 | 0.1814 |
| 1.1339 | 9.0 | 27000 | 1.1396 | 0.4053 | 0.1820 |
| 0.4781 | 10.0 | 30000 | 1.1755 | 0.4003 | 0.1805 |
| 1.0246 | 11.0 | 33000 | 1.1920 | 0.4027 | 0.1808 |
| 0.9689 | 12.0 | 36000 | 1.1900 | 0.4014 | 0.1797 |
Framework versions
- Transformers 4.55.2
- Pytorch 2.7.0+cu126
- Datasets 2.19.1
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Aug 25, 2025
- Updated
- Aug 25, 2025