Downloads · 30 days
9
38% of all-time downloads
tts_1e-5
nijes/tts_1e-5
tts_1e-5 is a automatic speech recognition model from nijes. 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
24
Public
Parameters
242M
967 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 9, 2025
- Updated
- Aug 9, 2025
- SHA
- 4696b241
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. -->
nijes/tts_1e-5
This model is a fine-tuned version of openai/whisper-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1367
- Cer: 6.0251
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.3796 | 1.0 | 1114 | 0.2136 | 9.3303 |
| 0.2795 | 2.0 | 2228 | 0.1687 | 8.4162 |
| 0.1925 | 3.0 | 3342 | 0.1548 | 7.3416 |
| 0.1683 | 4.0 | 4456 | 0.1467 | 6.7498 |
| 0.1086 | 5.0 | 5570 | 0.1422 | 6.7682 |
| 0.112 | 6.0 | 6684 | 0.1391 | 6.5946 |
| 0.11 | 7.0 | 7798 | 0.1376 | 5.8909 |
| 0.0788 | 8.0 | 8912 | 0.1373 | 5.7423 |
| 0.1071 | 9.0 | 10026 | 0.1371 | 5.9436 |
| 0.0703 | 10.0 | 11140 | 0.1367 | 6.0251 |
Framework versions
- Transformers 4.53.0
- Pytorch 2.5.1+cu124
- Datasets 3.5.1
- Tokenizers 0.21.4
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 9, 2025
- Updated
- Aug 9, 2025