Downloads · 30 days
13
33% of all-time downloads
STT-swedish-attention-dropout-model
Neprox/STT-swedish-attention-dropout-model
STT-swedish-attention-dropout-model is a automatic speech recognition model from Neprox. 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
40
Public
Repo size
5.8 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
- Dec 5, 2022
- Updated
- Dec 5, 2022
- SHA
- cc02d731
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 Small - Swedish
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: 0.3500
- Wer: 19.5235
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1391 | 1.3 | 1000 | 0.2981 | 21.5939 |
| 0.049 | 2.59 | 2000 | 0.2954 | 20.5614 |
| 0.0198 | 3.89 | 3000 | 0.3049 | 19.9564 |
| 0.0036 | 5.18 | 4000 | 0.3381 | 19.6042 |
| 0.0024 | 6.48 | 5000 | 0.3500 | 19.5235 |
Framework versions
- Transformers 4.25.0.dev0
- Pytorch 1.12.1
- Datasets 2.7.1
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- whisper
- License
- apache-2.0
- Languages
- sv
- Created
- Dec 5, 2022
- Updated
- Dec 5, 2022