Commit
•
dd38d70
1
Parent(s):
fad7184
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-as-v9
|
| 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-as-v9
|
| 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: 1.1679
|
| 20 |
+
- Wer: 0.5761
|
| 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: 300
|
| 48 |
+
- num_epochs: 200
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:----:|:---------------:|:------:|
|
| 55 |
+
| 8.3852 | 10.51 | 200 | 3.6402 | 1.0 |
|
| 56 |
+
| 3.5374 | 21.05 | 400 | 3.3894 | 1.0 |
|
| 57 |
+
| 2.8645 | 31.56 | 600 | 1.3143 | 0.8303 |
|
| 58 |
+
| 1.1784 | 42.1 | 800 | 0.9417 | 0.6661 |
|
| 59 |
+
| 0.7805 | 52.62 | 1000 | 0.9292 | 0.6237 |
|
| 60 |
+
| 0.5973 | 63.15 | 1200 | 0.9489 | 0.6014 |
|
| 61 |
+
| 0.4784 | 73.67 | 1400 | 0.9916 | 0.5962 |
|
| 62 |
+
| 0.4138 | 84.21 | 1600 | 1.0272 | 0.6121 |
|
| 63 |
+
| 0.3491 | 94.72 | 1800 | 1.0412 | 0.5984 |
|
| 64 |
+
| 0.3062 | 105.26 | 2000 | 1.0769 | 0.6005 |
|
| 65 |
+
| 0.2707 | 115.77 | 2200 | 1.0708 | 0.5752 |
|
| 66 |
+
| 0.2459 | 126.31 | 2400 | 1.1285 | 0.6009 |
|
| 67 |
+
| 0.2234 | 136.82 | 2600 | 1.1209 | 0.5949 |
|
| 68 |
+
| 0.2035 | 147.36 | 2800 | 1.1348 | 0.5842 |
|
| 69 |
+
| 0.1876 | 157.87 | 3000 | 1.1480 | 0.5872 |
|
| 70 |
+
| 0.1669 | 168.41 | 3200 | 1.1496 | 0.5838 |
|
| 71 |
+
| 0.1595 | 178.92 | 3400 | 1.1721 | 0.5778 |
|
| 72 |
+
| 0.1505 | 189.46 | 3600 | 1.1654 | 0.5744 |
|
| 73 |
+
| 0.1486 | 199.97 | 3800 | 1.1679 | 0.5761 |
|
| 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
|