Downloads · 30 days
7
37% of all-time downloads
xlsr53-cv-1
lejonck/xlsr53-cv-1
xlsr53-cv-1 is a automatic speech recognition model from lejonck. 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
19
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
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025
- SHA
- 06b729b1
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. -->
xlsr53-cv-1
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53-portuguese on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.2616
- Wer: 0.1801
- Cer: 0.0755
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 |
|---|---|---|---|---|---|
| 0.5877 | 1.0 | 3000 | 0.2979 | 0.2887 | 0.1613 |
| 0.4295 | 2.0 | 6000 | 0.2664 | 0.2218 | 0.0955 |
| 0.2141 | 3.0 | 9000 | 0.2586 | 0.2033 | 0.0864 |
| 0.2704 | 4.0 | 12000 | 0.2600 | 0.1971 | 0.0837 |
| 0.2645 | 5.0 | 15000 | 0.2515 | 0.1969 | 0.0824 |
| 0.2537 | 6.0 | 18000 | 0.2491 | 0.1920 | 0.0809 |
| 0.2388 | 7.0 | 21000 | 0.2580 | 0.1853 | 0.0774 |
| 0.0972 | 8.0 | 24000 | 0.2583 | 0.1868 | 0.0811 |
| 0.1854 | 9.0 | 27000 | 0.2637 | 0.1841 | 0.0780 |
| 0.1369 | 10.0 | 30000 | 0.2636 | 0.1811 | 0.0766 |
| 0.3859 | 11.0 | 33000 | 0.2616 | 0.1801 | 0.0755 |
| 0.11 | 12.0 | 36000 | 0.2623 | 0.1801 | 0.0758 |
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
- License
- apache-2.0
- Created
- Aug 21, 2025
- Updated
- Aug 21, 2025