Downloads · 30 days
3
3% of all-time downloads
1-epochs8.0-char-based-freeze_cnn-dropout0.1
tuanio/1-epochs8.0-char-based-freeze_cnn-dropout0.1
1-epochs8.0-char-based-freeze_cnn-dropout0.1 is a automatic speech recognition model from tuanio. 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
116
Public
Repo size
75.7 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
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Oct 29, 2023
- Updated
- Oct 29, 2023
- SHA
- 64f3386f
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. -->
1-epochs8.0-char-based-freeze_cnn-dropout0.1
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5088
- Wer: 0.3569
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: 2e-05
- train_batch_size: 10
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- total_train_batch_size: 40
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 8.0
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.3362 | 0.69 | 2500 | 3.5583 | 1.0 |
| 2.0051 | 1.37 | 5000 | 1.7739 | 0.9582 |
| 1.159 | 2.06 | 7500 | 0.8389 | 0.6072 |
| 1.0512 | 2.75 | 10000 | 0.6869 | 0.4956 |
| 0.924 | 3.44 | 12500 | 0.6140 | 0.4428 |
| 0.8536 | 4.12 | 15000 | 0.5817 | 0.4121 |
| 0.8607 | 4.81 | 17500 | 0.5506 | 0.3896 |
| 0.8019 | 5.5 | 20000 | 0.5279 | 0.3732 |
| 0.8105 | 6.19 | 22500 | 0.5264 | 0.3612 |
| 0.881 | 6.87 | 25000 | 0.5102 | 0.3605 |
| 0.7724 | 7.56 | 27500 | 0.5088 | 0.3569 |
Framework versions
- Transformers 4.34.0
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.14.1
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Oct 29, 2023
- Updated
- Oct 29, 2023