Downloads · 30 days
5
28% of all-time downloads
akan-wd-1
devkyle/akan-wd-1
akan-wd-1 is a automatic speech recognition model from devkyle. 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
18
Public
Parameters
37.8M
756 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors151 MB · 99%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Sep 10, 2024
- Updated
- Sep 12, 2024
- SHA
- 0470ae07
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-tiny-akan-100
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1823
- Wer: 8.7755
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1101 | 8.3333 | 500 | 0.9455 | 59.9493 |
| 0.0295 | 16.6667 | 1000 | 1.0721 | 50.0664 |
| 0.0117 | 25.0 | 1500 | 1.1477 | 50.5491 |
| 0.0008 | 33.3333 | 2000 | 1.1674 | 47.4840 |
| 0.0016 | 41.6667 | 2500 | 0.1804 | 9.2610 |
| 0.0004 | 50.0 | 3000 | 0.1823 | 8.7755 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Created
- Sep 10, 2024
- Updated
- Sep 12, 2024