đ xls-r-300m-te
This model is a fine - tuned version of facebook/wav2vec2-xls-r-300m on the OPENSLR_SLR66 - NA dataset. It's designed for automatic speech recognition and has achieved certain results on the evaluation set, offering value in speech - related tasks.
⨠Features
- Fine - Tuned Model: Based on facebook/wav2vec2-xls-r-300m, fine - tuned on the OPENSLR_SLR66 - NA dataset.
- Multiple Metrics: Evaluated by metrics such as WER (Word Error Rate) and CER (Character Error Rate).
đĻ Installation
No installation steps are provided in the original document, so this section is skipped.
đģ Usage Examples
No code examples are provided in the original document, so this section is skipped.
đ Documentation
Model Performance
This model achieves the following results on the evaluation set:
Model Index
| Property |
Details |
| Name |
xls-r-300m-te |
| Task Type |
automatic - speech - recognition |
| Dataset Type |
openslr |
| Dataset Name |
Open SLR (args: SLR66) |
| Metrics (WER) |
24.695121951219512 (Test WER) |
| Metrics (CER) |
4.861934182322532 (Test CER) |
Training and Evaluation Data
The model uses datasets from openslr and SLR66. However, more detailed information is not provided in the original document.
Training Procedure
Training Hyperparameters
The following hyperparameters were used during training:
- learning_rate: 7.5e - 05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon = 1e - 08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training Results
| Training Loss |
Epoch |
Step |
Validation Loss |
Wer |
| 3.0304 |
4.81 |
500 |
1.5676 |
1.0554 |
| 1.5263 |
9.61 |
1000 |
0.4693 |
0.8023 |
| 1.5299 |
14.42 |
1500 |
0.4368 |
0.7311 |
| 1.5063 |
19.23 |
2000 |
0.4360 |
0.7302 |
| 1.455 |
24.04 |
2500 |
0.4213 |
0.6692 |
| 1.4755 |
28.84 |
3000 |
0.4329 |
0.5943 |
| 1.352 |
33.65 |
3500 |
0.4074 |
0.5765 |
| 1.3122 |
38.46 |
4000 |
0.3866 |
0.5630 |
| 1.2799 |
43.27 |
4500 |
0.3860 |
0.5480 |
| 1.212 |
48.08 |
5000 |
0.3590 |
0.5317 |
| 1.1645 |
52.88 |
5500 |
0.3283 |
0.4757 |
| 1.0854 |
57.69 |
6000 |
0.3162 |
0.4687 |
| 1.0292 |
62.5 |
6500 |
0.3126 |
0.4416 |
| 0.9607 |
67.31 |
7000 |
0.2990 |
0.4066 |
| 0.9156 |
72.12 |
7500 |
0.2870 |
0.4009 |
| 0.8329 |
76.92 |
8000 |
0.2791 |
0.3909 |
| 0.7979 |
81.73 |
8500 |
0.2770 |
0.3670 |
| 0.7144 |
86.54 |
9000 |
0.2841 |
0.3661 |
| 0.6997 |
91.35 |
9500 |
0.2721 |
0.3485 |
| 0.6568 |
96.15 |
10000 |
0.2681 |
0.3437 |
Framework Versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0
đ§ Technical Details
No detailed technical implementation information (more than 50 words) is provided in the original document, so this section is skipped.
đ License
This model is under the Apache - 2.0 license.
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
