Downloads · 30 days
6
9% of all-time downloads
in_car_commands_26_mdl__base_ver2
Angeriod/in_car_commands_26_mdl__base_ver2
in_car_commands_26_mdl__base_ver2 is a automatic speech recognition model from Angeriod. 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
70
Public
Parameters
72.6M
7.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jan 16, 2025
- Updated
- Jan 17, 2025
- SHA
- cb7a512e
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. -->
in_car_commands_26_mdl__base_ver2
This model is a fine-tuned version of openai/whisper-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0413
- Cer: 5.4586
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: 3.75e-05
- train_batch_size: 16
- eval_batch_size: 16
- 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: 500
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.1208 | 1.0 | 2000 | 0.1080 | 11.5171 |
| 0.0519 | 2.0 | 4000 | 0.0671 | 9.6709 |
| 0.0313 | 3.0 | 6000 | 0.0533 | 7.8856 |
| 0.0185 | 4.0 | 8000 | 0.0455 | 8.0669 |
| 0.0103 | 5.0 | 10000 | 0.0438 | 7.0337 |
| 0.0039 | 6.0 | 12000 | 0.0438 | 6.6026 |
| 0.0014 | 7.0 | 14000 | 0.0427 | 6.1767 |
| 0.0004 | 8.0 | 16000 | 0.0419 | 5.6847 |
| 0.0002 | 9.0 | 18000 | 0.0419 | 6.4667 |
| 0.0001 | 10.0 | 20000 | 0.0418 | 6.3877 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Jan 16, 2025
- Updated
- Jan 17, 2025