Downloads · 30 days
5
23% of all-time downloads
m14_main
Sjdan/m14_main
m14_main is a automatic speech recognition model from Sjdan. 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
22
Public
Repo size
2.5 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
- Feb 19, 2023
- Updated
- Feb 20, 2023
- SHA
- c08e2bc9
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. -->
m14_main
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0139
- Wer: 1.7222
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: 0.0001
- train_batch_size: 8
- 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: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 9.5522 | 0.96 | 500 | 3.1735 | 1.0 |
| 2.78 | 1.92 | 1000 | 2.0292 | 2.8356 |
| 1.2155 | 2.88 | 1500 | 0.5523 | 2.4933 |
| 0.3803 | 3.84 | 2000 | 0.1129 | 1.8756 |
| 0.161 | 4.8 | 2500 | 0.0486 | 1.8289 |
| 0.0825 | 5.76 | 3000 | 0.0244 | 1.7222 |
| 0.0721 | 6.72 | 3500 | 0.0139 | 1.7222 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- wav2vec2
- License
- apache-2.0
- Created
- Feb 19, 2023
- Updated
- Feb 20, 2023