Downloads · 30 days
4
15% of all-time downloads
whisper-medium-ee-med-test5
jaaklember/whisper-medium-ee-med-test5
whisper-medium-ee-med-test5 is a automatic speech recognition model from jaaklember. 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
27
Public
Parameters
764M
21.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024
- SHA
- 92ab1473
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 medium ET medical (test5)
This model is a fine-tuned version of openai/whisper-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0398
- Wer: 5.9880
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: 3
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.4808 | 1.0 | 11 | 0.4336 | 27.5449 |
| 0.7116 | 2.0 | 22 | 0.1104 | 9.5808 |
| 0.1563 | 3.0 | 33 | 0.0670 | 8.3832 |
| 0.0585 | 4.0 | 44 | 0.0487 | 5.3892 |
| 0.0483 | 5.0 | 55 | 0.0552 | 7.7844 |
| 0.0099 | 6.0 | 66 | 0.0433 | 6.5868 |
| 0.0033 | 7.0 | 77 | 0.0415 | 5.3892 |
| 0.0017 | 8.0 | 88 | 0.0413 | 5.9880 |
| 0.001 | 9.0 | 99 | 0.0406 | 5.9880 |
| 0.0009 | 10.0 | 110 | 0.0398 | 5.9880 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- et
- Created
- Oct 18, 2024
- Updated
- Oct 18, 2024