Commit
•
49a018e
1
Parent(s):
a03ceb5
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-hsb-v3
|
| 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-hsb-v3
|
| 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: 0.6549
|
| 20 |
+
- Wer: 0.4827
|
| 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: 0.00045
|
| 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: 50
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 8.8951 | 3.23 | 100 | 3.6396 | 1.0 |
|
| 56 |
+
| 3.314 | 6.45 | 200 | 3.2331 | 1.0 |
|
| 57 |
+
| 3.1931 | 9.68 | 300 | 3.0947 | 0.9906 |
|
| 58 |
+
| 1.7079 | 12.9 | 400 | 0.8865 | 0.8499 |
|
| 59 |
+
| 0.6859 | 16.13 | 500 | 0.7994 | 0.7529 |
|
| 60 |
+
| 0.4804 | 19.35 | 600 | 0.7783 | 0.7069 |
|
| 61 |
+
| 0.3506 | 22.58 | 700 | 0.6904 | 0.6321 |
|
| 62 |
+
| 0.2695 | 25.81 | 800 | 0.6519 | 0.5926 |
|
| 63 |
+
| 0.222 | 29.03 | 900 | 0.7041 | 0.5720 |
|
| 64 |
+
| 0.1828 | 32.26 | 1000 | 0.6608 | 0.5513 |
|
| 65 |
+
| 0.1474 | 35.48 | 1100 | 0.7129 | 0.5319 |
|
| 66 |
+
| 0.1269 | 38.71 | 1200 | 0.6664 | 0.5056 |
|
| 67 |
+
| 0.1077 | 41.94 | 1300 | 0.6712 | 0.4942 |
|
| 68 |
+
| 0.0934 | 45.16 | 1400 | 0.6467 | 0.4879 |
|
| 69 |
+
| 0.0819 | 48.39 | 1500 | 0.6549 | 0.4827 |
|
| 70 |
+
|
| 71 |
+
|
| 72 |
+
### Framework versions
|
| 73 |
+
|
| 74 |
+
- Transformers 4.16.1
|
| 75 |
+
- Pytorch 1.10.0+cu111
|
| 76 |
+
- Datasets 1.18.2
|
| 77 |
+
- Tokenizers 0.11.0
|