Downloads · 30 days
5
16% of all-time downloads
Model_G_S_Berita_Wav2Vec2_Version2
rossevine/Model_G_S_Berita_Wav2Vec2_Version2
Model_G_S_Berita_Wav2Vec2_Version2 is a automatic speech recognition model from rossevine. Use it when you need speech turned into text. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
32
Public
Repo size
5 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin1.3 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- Model type
- wav2vec2
- Access
- Public
- Created
- Aug 19, 2023
- Updated
- Aug 19, 2023
- SHA
- 1cc1e391
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. -->
Model_G_S_Berita_Wav2Vec2_Version2
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4915
- Wer: 0.4678
- Cer: 0.0902
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 0.3249 | 13.79 | 400 | 0.4083 | 0.4049 | 0.0769 |
| 0.0209 | 27.59 | 800 | 0.4915 | 0.4678 | 0.0902 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.18.3
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- Created
- Aug 19, 2023
- Updated
- Aug 19, 2023