Downloads · 30 days
8
24% of all-time downloads
whisper-medium-tigre-colab-CV17.0
ndeclarke/whisper-medium-tigre-colab-CV17.0
whisper-medium-tigre-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
33
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 27, 2024
- Updated
- Aug 27, 2024
- SHA
- ea269185
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-tigre-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: 0.6204
- Wer: 0.4909
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: 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 |
|---|---|---|---|---|
| 1.3461 | 6.8966 | 200 | 0.4180 | 0.7040 |
| 0.0668 | 13.7931 | 400 | 0.4826 | 0.5938 |
| 0.016 | 20.6897 | 600 | 0.5556 | 0.5656 |
| 0.0068 | 27.5862 | 800 | 0.6085 | 0.5291 |
| 0.0029 | 34.4828 | 1000 | 0.5854 | 0.5091 |
| 0.0005 | 41.3793 | 1200 | 0.6063 | 0.4991 |
| 0.0 | 48.2759 | 1400 | 0.6148 | 0.5 |
| 0.0 | 55.1724 | 1600 | 0.6183 | 0.4918 |
| 0.0 | 62.0690 | 1800 | 0.6199 | 0.4927 |
| 0.0 | 68.9655 | 2000 | 0.6204 | 0.4909 |
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 27, 2024
- Updated
- Aug 27, 2024