Commit
•
6dede90
1
Parent(s):
7fdc441
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: wav2vec2-large-xls-r-300m-bas-v1
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# wav2vec2-large-xls-r-300m-bas-v1
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.5997
|
| 20 |
+
- Wer: 0.3870
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 0.000111
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 32
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 500
|
| 48 |
+
- num_epochs: 100
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 12.7076 | 5.26 | 200 | 3.6361 | 1.0 |
|
| 56 |
+
| 3.1657 | 10.52 | 400 | 3.0101 | 1.0 |
|
| 57 |
+
| 2.3987 | 15.78 | 600 | 0.9125 | 0.6774 |
|
| 58 |
+
| 1.0079 | 21.05 | 800 | 0.6477 | 0.5352 |
|
| 59 |
+
| 0.7392 | 26.31 | 1000 | 0.5432 | 0.4929 |
|
| 60 |
+
| 0.6114 | 31.57 | 1200 | 0.5498 | 0.4639 |
|
| 61 |
+
| 0.5222 | 36.83 | 1400 | 0.5220 | 0.4561 |
|
| 62 |
+
| 0.4648 | 42.1 | 1600 | 0.5586 | 0.4289 |
|
| 63 |
+
| 0.4103 | 47.36 | 1800 | 0.5337 | 0.4082 |
|
| 64 |
+
| 0.3692 | 52.62 | 2000 | 0.5421 | 0.3861 |
|
| 65 |
+
| 0.3403 | 57.88 | 2200 | 0.5549 | 0.4096 |
|
| 66 |
+
| 0.3011 | 63.16 | 2400 | 0.5833 | 0.3925 |
|
| 67 |
+
| 0.2932 | 68.42 | 2600 | 0.5674 | 0.3815 |
|
| 68 |
+
| 0.2696 | 73.68 | 2800 | 0.5734 | 0.3889 |
|
| 69 |
+
| 0.2496 | 78.94 | 3000 | 0.5968 | 0.3985 |
|
| 70 |
+
| 0.2289 | 84.21 | 3200 | 0.5888 | 0.3893 |
|
| 71 |
+
| 0.2091 | 89.47 | 3400 | 0.5849 | 0.3852 |
|
| 72 |
+
| 0.2005 | 94.73 | 3600 | 0.5938 | 0.3875 |
|
| 73 |
+
| 0.1876 | 99.99 | 3800 | 0.5997 | 0.3870 |
|
| 74 |
+
|
| 75 |
+
|
| 76 |
+
### Framework versions
|
| 77 |
+
|
| 78 |
+
- Transformers 4.16.1
|
| 79 |
+
- Pytorch 1.10.0+cu111
|
| 80 |
+
- Datasets 1.18.2
|
| 81 |
+
- Tokenizers 0.11.0
|