Commit
•
0b4f67c
1
Parent(s):
d983b55
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- common_voice
|
| 7 |
+
model-index:
|
| 8 |
+
- name: ''
|
| 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 |
+
#
|
| 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: 0.3086
|
| 20 |
+
- Wer: 0.2676
|
| 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: 7.5e-05
|
| 40 |
+
- train_batch_size: 32
|
| 41 |
+
- eval_batch_size: 16
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 1500
|
| 46 |
+
- num_epochs: 60.0
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 5.175 | 2.41 | 400 | 4.6909 | 1.0 |
|
| 54 |
+
| 3.3785 | 4.82 | 800 | 3.3080 | 1.0 |
|
| 55 |
+
| 2.6964 | 7.23 | 1200 | 2.0651 | 1.1055 |
|
| 56 |
+
| 1.3008 | 9.64 | 1600 | 0.5845 | 0.6207 |
|
| 57 |
+
| 1.1185 | 12.05 | 2000 | 0.4195 | 0.4193 |
|
| 58 |
+
| 1.0252 | 14.46 | 2400 | 0.3824 | 0.3570 |
|
| 59 |
+
| 0.935 | 16.87 | 2800 | 0.3693 | 0.3462 |
|
| 60 |
+
| 0.8818 | 19.28 | 3200 | 0.3587 | 0.3318 |
|
| 61 |
+
| 0.8534 | 21.69 | 3600 | 0.3420 | 0.3180 |
|
| 62 |
+
| 0.8137 | 24.1 | 4000 | 0.3426 | 0.3130 |
|
| 63 |
+
| 0.7968 | 26.51 | 4400 | 0.3349 | 0.3102 |
|
| 64 |
+
| 0.7558 | 28.92 | 4800 | 0.3216 | 0.3019 |
|
| 65 |
+
| 0.7313 | 31.33 | 5200 | 0.3451 | 0.3060 |
|
| 66 |
+
| 0.7358 | 33.73 | 5600 | 0.3272 | 0.2967 |
|
| 67 |
+
| 0.718 | 36.14 | 6000 | 0.3315 | 0.2882 |
|
| 68 |
+
| 0.6991 | 38.55 | 6400 | 0.3299 | 0.2830 |
|
| 69 |
+
| 0.6529 | 40.96 | 6800 | 0.3140 | 0.2836 |
|
| 70 |
+
| 0.6225 | 43.37 | 7200 | 0.3128 | 0.2751 |
|
| 71 |
+
| 0.633 | 45.78 | 7600 | 0.3211 | 0.2774 |
|
| 72 |
+
| 0.5876 | 48.19 | 8000 | 0.3162 | 0.2764 |
|
| 73 |
+
| 0.588 | 50.6 | 8400 | 0.3082 | 0.2722 |
|
| 74 |
+
| 0.5915 | 53.01 | 8800 | 0.3120 | 0.2681 |
|
| 75 |
+
| 0.5798 | 55.42 | 9200 | 0.3133 | 0.2709 |
|
| 76 |
+
| 0.5736 | 57.83 | 9600 | 0.3086 | 0.2676 |
|
| 77 |
+
|
| 78 |
+
|
| 79 |
+
### Framework versions
|
| 80 |
+
|
| 81 |
+
- Transformers 4.17.0.dev0
|
| 82 |
+
- Pytorch 1.10.2+cu102
|
| 83 |
+
- Datasets 1.18.4.dev0
|
| 84 |
+
- Tokenizers 0.11.0
|