Downloads · 30 days
2
2% of all-time downloads
wav2vec2-large-xls-r-300m-dm32-improve
SucharithaS/wav2vec2-large-xls-r-300m-dm32-improve
wav2vec2-large-xls-r-300m-dm32-improve is a machine learning model from SucharithaS. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
86
Public
Parameters
316M
3.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- ebe2447f
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. -->
wav2vec2-large-xls-r-300m-dm32-improve
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4316
- Accuracy: 0.7917
- F1: 0.7786
- Precision: 0.8194
- Recall: 0.7917
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
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 22
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 2.34 | 34 | 0.6946 | 0.4167 | 0.2451 | 0.1736 | 0.4167 |
| No log | 4.69 | 68 | 0.6802 | 0.5833 | 0.4298 | 0.3403 | 0.5833 |
| No log | 7.03 | 102 | 0.6835 | 0.5833 | 0.4298 | 0.3403 | 0.5833 |
| 0.6993 | 9.38 | 136 | 0.6839 | 0.6042 | 0.5040 | 0.6278 | 0.6042 |
| 0.6993 | 11.72 | 170 | 0.6771 | 0.5833 | 0.4298 | 0.3403 | 0.5833 |
| 0.6993 | 14.07 | 204 | 0.6801 | 0.5417 | 0.4641 | 0.4722 | 0.5417 |
| 0.6876 | 16.41 | 238 | 0.6758 | 0.5833 | 0.4298 | 0.3403 | 0.5833 |
| 0.6876 | 18.76 | 272 | 0.4094 | 0.8333 | 0.8267 | 0.8501 | 0.8333 |
| 0.6876 | 21.1 | 306 | 0.4316 | 0.7917 | 0.7786 | 0.8194 | 0.7917 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.15.2
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026