Downloads · 30 days
4
9% of all-time downloads
whisper-medium-yoruba-colab-CV17.0
ndeclarke/whisper-medium-yoruba-colab-CV17.0
whisper-medium-yoruba-colab-CV17.0 is a machine learning model from ndeclarke. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
47
Public
Parameters
764M
15.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024
- SHA
- b14989ed
Base models
Datasets
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-yoruba-colab-CV17.0
This model is a fine-tuned version of openai/whisper-medium on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.8837
- Wer: 0.5795
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: 5e-05
- 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_ratio: 0.15
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 1.1598 | 1.5385 | 200 | 0.7392 | 0.7048 |
| 0.398 | 3.0769 | 400 | 0.7344 | 0.7034 |
| 0.1932 | 4.6154 | 600 | 0.7691 | 0.6540 |
| 0.1032 | 6.1538 | 800 | 0.8190 | 0.6376 |
| 0.0542 | 7.6923 | 1000 | 0.8399 | 0.6544 |
| 0.0287 | 9.2308 | 1200 | 0.8402 | 0.6343 |
| 0.0156 | 10.7692 | 1400 | 0.8548 | 0.5978 |
| 0.0053 | 12.3077 | 1600 | 0.8853 | 0.5902 |
| 0.0013 | 13.8462 | 1800 | 0.8801 | 0.5816 |
| 0.0006 | 15.3846 | 2000 | 0.8837 | 0.5795 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- whisper
- License
- apache-2.0
- Created
- Aug 28, 2024
- Updated
- Aug 28, 2024