Downloads · 30 days
4
11% of all-time downloads
wav2vec2-base-timit
npallewela/wav2vec2-base-timit
wav2vec2-base-timit is a automatic speech recognition model from npallewela. 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
37
Public
Parameters
94.4M
378 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors378 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025
- SHA
- ca438fd6
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-base demo - Nuwan
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4837
- Wer: 0.2932
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 10
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.8119 | 0.8772 | 100 | 0.7517 | 0.5877 |
| 0.6048 | 1.7544 | 200 | 0.5188 | 0.4507 |
| 0.3757 | 2.6316 | 300 | 0.4527 | 0.3911 |
| 0.2723 | 3.5088 | 400 | 0.4244 | 0.3730 |
| 0.201 | 4.3860 | 500 | 0.4285 | 0.3570 |
| 0.1673 | 5.2632 | 600 | 0.4191 | 0.3491 |
| 0.1376 | 6.1404 | 700 | 0.4138 | 0.3359 |
| 0.1207 | 7.0175 | 800 | 0.4201 | 0.3276 |
| 0.1062 | 7.8947 | 900 | 0.4203 | 0.3224 |
| 0.0904 | 8.7719 | 1000 | 0.4377 | 0.3243 |
| 0.0769 | 9.6491 | 1100 | 0.4207 | 0.3186 |
| 0.0761 | 10.5263 | 1200 | 0.4357 | 0.3153 |
| 0.0695 | 11.4035 | 1300 | 0.4268 | 0.3113 |
| 0.0628 | 12.2807 | 1400 | 0.4365 | 0.3112 |
| 0.0616 | 13.1579 | 1500 | 0.4552 | 0.3122 |
| 0.0527 | 14.0351 | 1600 | 0.4504 | 0.3057 |
| 0.0545 | 14.9123 | 1700 | 0.4545 | 0.3085 |
| 0.0489 | 15.7895 | 1800 | 0.4650 | 0.3100 |
| 0.0453 | 16.6667 | 1900 | 0.4364 | 0.3046 |
| 0.042 | 17.5439 | 2000 | 0.4629 | 0.3064 |
| 0.0401 | 18.4211 | 2100 | 0.4764 | 0.3067 |
| 0.0383 | 19.2982 | 2200 | 0.4638 | 0.3018 |
| 0.0343 | 20.1754 | 2300 | 0.4760 | 0.2992 |
| 0.0322 | 21.0526 | 2400 | 0.4854 | 0.3010 |
| 0.0317 | 21.9298 | 2500 | 0.4758 | 0.2984 |
| 0.0318 | 22.8070 | 2600 | 0.4760 | 0.2964 |
| 0.0308 | 23.6842 | 2700 | 0.4947 | 0.2962 |
| 0.0262 | 24.5614 | 2800 | 0.4842 | 0.2960 |
| 0.0273 | 25.4386 | 2900 | 0.4903 | 0.2935 |
| 0.0257 | 26.3158 | 3000 | 0.4819 | 0.2951 |
| 0.025 | 27.1930 | 3100 | 0.4736 | 0.2932 |
| 0.023 | 28.0702 | 3200 | 0.4883 | 0.2923 |
| 0.0233 | 28.9474 | 3300 | 0.4848 | 0.2933 |
| 0.0242 | 29.8246 | 3400 | 0.4837 | 0.2932 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Languages
- en
- Created
- Nov 24, 2025
- Updated
- Nov 24, 2025