Downloads · 30 days
5
29% of all-time downloads
xlsr53-coraa-1
lejonck/xlsr53-coraa-1
xlsr53-coraa-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
17
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 25, 2025
- Updated
- Aug 25, 2025
- SHA
- 8993da50
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-coraa-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: 1.2737
- Wer: 0.4291
- Cer: 0.1950
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 |
|---|---|---|---|---|---|
| 1.757 | 1.0 | 2000 | 1.3578 | 0.5140 | 0.2361 |
| 1.1274 | 2.0 | 4000 | 1.2848 | 0.4803 | 0.2172 |
| 1.7319 | 3.0 | 6000 | 1.2512 | 0.4612 | 0.2117 |
| 1.1822 | 4.0 | 8000 | 1.2447 | 0.4536 | 0.2047 |
| 1.805 | 5.0 | 10000 | 1.2562 | 0.4457 | 0.2026 |
| 1.0604 | 6.0 | 12000 | 1.2624 | 0.4351 | 0.2001 |
| 1.5226 | 7.0 | 14000 | 1.2306 | 0.4371 | 0.1979 |
| 1.6228 | 8.0 | 16000 | 1.2694 | 0.4351 | 0.1969 |
| 1.3507 | 9.0 | 18000 | 1.2737 | 0.4291 | 0.1949 |
| 1.2509 | 10.0 | 20000 | 1.2972 | 0.4311 | 0.1944 |
| 1.5327 | 11.0 | 22000 | 1.2962 | 0.4301 | 0.1941 |
| 1.4476 | 12.0 | 24000 | 1.3015 | 0.4328 | 0.1937 |
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 25, 2025
- Updated
- Aug 25, 2025