Downloads · 30 days
7
15% of all-time downloads
whisper-base-wer
adrianSauer/whisper-base-wer
whisper-base-wer is a automatic speech recognition model from adrianSauer. 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
46
Public
Parameters
72.6M
871 MB 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
- Mar 17, 2024
- Updated
- Aug 19, 2024
- SHA
- d5a11bf3
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. -->
Common Voice 16 - Guarani
This model is a fine-tuned version of openai/whisper-base on the Common Voice 16 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5857
- Wer: 58.1798
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant_with_warmup
- lr_scheduler_warmup_steps: 50
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.3905 | 1.0101 | 100 | 0.9598 | 81.9654 |
| 0.5779 | 2.0202 | 200 | 0.6883 | 68.6767 |
| 0.3116 | 3.0303 | 300 | 0.5997 | 62.5349 |
| 0.1741 | 4.0404 | 400 | 0.5750 | 59.5757 |
| 0.0955 | 5.0505 | 500 | 0.5857 | 58.1798 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- gn
- Created
- Mar 17, 2024
- Updated
- Aug 19, 2024