|
--- |
|
language: |
|
- he |
|
tags: |
|
- automatic-speech-recognition |
|
- robust-speech-event |
|
- he |
|
- generated_from_trainer |
|
model-index: |
|
- name: wav2vec2-xls-r-300m-hebrew |
|
results: [] |
|
--- |
|
|
|
<!-- 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-xls-r-300m-hebrew |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the private dataset with stats: |
|
|
|
| split |size | n_samples | duration(hrs)| | |
|
|---|---|---|---|---| |
|
|train|4.19gb| 20306 | 28 | | |
|
|dev |1.05gb| 5076 | 7 | | |
|
|
|
|
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5438 |
|
- Wer: 0.1773 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1000 |
|
- num_epochs: 100.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| No log | 3.15 | 1000 | 0.5203 | 0.4333 | |
|
| 1.4284 | 6.31 | 2000 | 0.4816 | 0.3951 | |
|
| 1.4284 | 9.46 | 3000 | 0.4315 | 0.3546 | |
|
| 1.283 | 12.62 | 4000 | 0.4278 | 0.3404 | |
|
| 1.283 | 15.77 | 5000 | 0.4090 | 0.3054 | |
|
| 1.1777 | 18.93 | 6000 | 0.3893 | 0.3006 | |
|
| 1.1777 | 22.08 | 7000 | 0.3968 | 0.2857 | |
|
| 1.0994 | 25.24 | 8000 | 0.3892 | 0.2751 | |
|
| 1.0994 | 28.39 | 9000 | 0.4061 | 0.2690 | |
|
| 1.0323 | 31.54 | 10000 | 0.4114 | 0.2507 | |
|
| 1.0323 | 34.7 | 11000 | 0.4021 | 0.2508 | |
|
| 0.9623 | 37.85 | 12000 | 0.4032 | 0.2378 | |
|
| 0.9623 | 41.01 | 13000 | 0.4148 | 0.2374 | |
|
| 0.9077 | 44.16 | 14000 | 0.4350 | 0.2323 | |
|
| 0.9077 | 47.32 | 15000 | 0.4515 | 0.2246 | |
|
| 0.8573 | 50.47 | 16000 | 0.4474 | 0.2180 | |
|
| 0.8573 | 53.63 | 17000 | 0.4649 | 0.2171 | |
|
| 0.8083 | 56.78 | 18000 | 0.4455 | 0.2102 | |
|
| 0.8083 | 59.94 | 19000 | 0.4587 | 0.2092 | |
|
| 0.769 | 63.09 | 20000 | 0.4794 | 0.2012 | |
|
| 0.769 | 66.25 | 21000 | 0.4845 | 0.2007 | |
|
| 0.7308 | 69.4 | 22000 | 0.4937 | 0.2008 | |
|
| 0.7308 | 72.55 | 23000 | 0.4920 | 0.1895 | |
|
| 0.6927 | 75.71 | 24000 | 0.5179 | 0.1911 | |
|
| 0.6927 | 78.86 | 25000 | 0.5202 | 0.1877 | |
|
| 0.6622 | 82.02 | 26000 | 0.5266 | 0.1840 | |
|
| 0.6622 | 85.17 | 27000 | 0.5351 | 0.1854 | |
|
| 0.6315 | 88.33 | 28000 | 0.5373 | 0.1811 | |
|
| 0.6315 | 91.48 | 29000 | 0.5331 | 0.1792 | |
|
| 0.6075 | 94.64 | 30000 | 0.5390 | 0.1779 | |
|
| 0.6075 | 97.79 | 31000 | 0.5459 | 0.1773 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu102 |
|
- Datasets 1.18.2.dev0 |
|
- Tokenizers 0.11.0 |
|
|
