Downloads · 30 days
7
14% of all-time downloads
whisper-base
luluw/whisper-base
whisper-base is a automatic speech recognition model from luluw. 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
51
Public
Parameters
72.6M
2.9 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
- Oct 4, 2024
- Updated
- Oct 4, 2024
- SHA
- 5fb32edc
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 Small
This model is a fine-tuned version of openai/whisper-base on the Personal - Mimic Recording dataset. It achieves the following results on the evaluation set:
- Loss: 0.2331
- Wer: 0.0992
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | Wer |
|---|---|---|---|---|
| 0.8867 | 1.0 | 74 | 0.5859 | 0.2243 |
| 0.4298 | 2.0 | 148 | 0.3974 | 0.1808 |
| 0.2678 | 3.0 | 222 | 0.3356 | 0.1572 |
| 0.1442 | 4.0 | 296 | 0.2868 | 0.1338 |
| 0.0591 | 5.0 | 370 | 0.2642 | 0.1229 |
| 0.0219 | 6.0 | 444 | 0.2568 | 0.1234 |
| 0.0123 | 7.0 | 518 | 0.2553 | 0.1164 |
| 0.0091 | 8.0 | 592 | 0.2419 | 0.0997 |
| 0.0046 | 9.0 | 666 | 0.2300 | 0.1004 |
| 0.0018 | 10.0 | 740 | 0.2331 | 0.0992 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.0
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- en
- Created
- Oct 4, 2024
- Updated
- Oct 4, 2024