Downloads · 30 days
17
3% of all-time downloads
whisper-small-sv-bm
birgermoell/whisper-small-sv-bm
whisper-small-sv-bm is a automatic speech recognition model from birgermoell. 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
657
Public
Repo size
11.6 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin967 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Nov 5, 2022
- Updated
- Nov 23, 2022
- SHA
- 0bcb4890
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. -->
WhisperSmallSwedishBirgerMoell
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.3253
- Wer: 19.5854
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_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1523 | 1.29 | 1000 | 0.2924 | 21.5509 |
| 0.0515 | 2.59 | 2000 | 0.2856 | 20.4593 |
| 0.0214 | 3.88 | 3000 | 0.3010 | 19.9054 |
| 0.0042 | 5.17 | 4000 | 0.3253 | 19.5854 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.6.1
- Tokenizers 0.13.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- sv
- Created
- Nov 5, 2022
- Updated
- Nov 23, 2022