Downloads · 30 days
5
18% of all-time downloads
wav2vec2-100libri-english
ykleeee/wav2vec2-100libri-english
wav2vec2-100libri-english is a automatic speech recognition model from ykleeee. 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
28
Public
Repo size
21.5 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
- License
- apache-2.0
- Model type
- wav2vec2
- Access
- Public
- Created
- Jan 30, 2023
- Updated
- Jan 31, 2023
- SHA
- 72bb250a
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. -->
wav2vec2-100libri-english
This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0786
- Wer: 0.1017
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.3602 | 0.28 | 1000 | 0.2307 | 0.2529 |
| 0.2774 | 0.56 | 2000 | 0.1332 | 0.1606 |
| 0.1765 | 0.84 | 3000 | 0.1256 | 0.1485 |
| 0.1488 | 1.12 | 4000 | 0.1179 | 0.1408 |
| 0.138 | 1.4 | 5000 | 0.1193 | 0.1348 |
| 0.1338 | 1.68 | 6000 | 0.1065 | 0.1336 |
| 0.125 | 1.96 | 7000 | 0.0977 | 0.1214 |
| 0.1048 | 2.24 | 8000 | 0.0975 | 0.1213 |
| 0.1222 | 2.52 | 9000 | 0.0917 | 0.1181 |
| 0.094 | 2.8 | 10000 | 0.0867 | 0.1144 |
| 0.0649 | 3.08 | 11000 | 0.0903 | 0.1127 |
| 0.0793 | 3.36 | 12000 | 0.0895 | 0.1106 |
| 0.0698 | 3.64 | 13000 | 0.0856 | 0.1094 |
| 0.0888 | 3.92 | 14000 | 0.0808 | 0.1058 |
| 0.0711 | 4.21 | 15000 | 0.0799 | 0.1053 |
| 0.0713 | 4.49 | 16000 | 0.0796 | 0.1024 |
| 0.0705 | 4.77 | 17000 | 0.0786 | 0.1017 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.1
- Datasets 2.8.0
- Tokenizers 0.10.3
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Jan 30, 2023
- Updated
- Jan 31, 2023