Downloads · 30 days
4
19% of all-time downloads
whisper-base-ea_1hrsd
Setosm/whisper-base-ea_1hrsd
whisper-base-ea_1hrsd is a automatic speech recognition model from Setosm. 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
21
Public
Parameters
72.6M
2.6 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
- May 19, 2025
- Updated
- May 19, 2025
- SHA
- a6c40ab5
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. -->
./whisper-base-ea-1hrsd
This model is a fine-tuned version of openai/whisper-base on the Afrispeech-200 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7341
- Wer Ortho: 0.3002
- Wer: 0.2495
- Cer: 0.1214
- Precision: 0.8529
- Recall: 0.8536
- F1: 0.8523
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: 16
- eval_batch_size: 8
- 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: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | Cer | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|---|---|
| 0.9512 | 0.3344 | 100 | 0.9677 | 0.3278 | 0.2780 | 0.1320 | 0.8298 | 0.8355 | 0.8319 |
| 0.7473 | 0.6689 | 200 | 0.8168 | 0.3054 | 0.2477 | 0.1169 | 0.8454 | 0.8479 | 0.8459 |
| 0.7431 | 1.0033 | 300 | 0.7681 | 0.2922 | 0.2427 | 0.1247 | 0.8537 | 0.8507 | 0.8512 |
| 0.5364 | 1.3378 | 400 | 0.7507 | 0.2946 | 0.2470 | 0.1240 | 0.8490 | 0.8484 | 0.8476 |
| 0.5233 | 1.6722 | 500 | 0.7341 | 0.3002 | 0.2495 | 0.1214 | 0.8529 | 0.8536 | 0.8523 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- May 19, 2025
- Updated
- May 19, 2025