Commit
•
d793b19
1
Parent(s):
6cfd555
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.8886
|
| 20 |
+
- Wer: 0.6657
|
| 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: 8
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- gradient_accumulation_steps: 2
|
| 44 |
+
- total_train_batch_size: 16
|
| 45 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
+
- lr_scheduler_type: linear
|
| 47 |
+
- lr_scheduler_warmup_steps: 50
|
| 48 |
+
- num_epochs: 50.0
|
| 49 |
+
- mixed_precision_training: Native AMP
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 55 |
+
| 10.1224 | 1.96 | 100 | 3.5429 | 1.0 |
|
| 56 |
+
| 3.2411 | 3.92 | 200 | 3.1786 | 1.0 |
|
| 57 |
+
| 3.1283 | 5.88 | 300 | 3.0571 | 1.0 |
|
| 58 |
+
| 3.0044 | 7.84 | 400 | 2.9560 | 0.9996 |
|
| 59 |
+
| 2.9388 | 9.8 | 500 | 2.8977 | 1.0011 |
|
| 60 |
+
| 2.86 | 11.76 | 600 | 2.6944 | 0.9952 |
|
| 61 |
+
| 2.5538 | 13.73 | 700 | 2.0967 | 0.9435 |
|
| 62 |
+
| 2.1214 | 15.69 | 800 | 1.4816 | 0.8428 |
|
| 63 |
+
| 1.8136 | 17.65 | 900 | 1.2459 | 0.8048 |
|
| 64 |
+
| 1.6795 | 19.61 | 1000 | 1.1232 | 0.7649 |
|
| 65 |
+
| 1.5571 | 21.57 | 1100 | 1.0510 | 0.7432 |
|
| 66 |
+
| 1.4975 | 23.53 | 1200 | 1.0298 | 0.6963 |
|
| 67 |
+
| 1.4485 | 25.49 | 1300 | 0.9775 | 0.7074 |
|
| 68 |
+
| 1.3924 | 27.45 | 1400 | 0.9798 | 0.6956 |
|
| 69 |
+
| 1.3604 | 29.41 | 1500 | 0.9345 | 0.7092 |
|
| 70 |
+
| 1.3224 | 31.37 | 1600 | 0.9535 | 0.6830 |
|
| 71 |
+
| 1.2816 | 33.33 | 1700 | 0.9178 | 0.6679 |
|
| 72 |
+
| 1.2623 | 35.29 | 1800 | 0.9249 | 0.6679 |
|
| 73 |
+
| 1.2421 | 37.25 | 1900 | 0.9124 | 0.6734 |
|
| 74 |
+
| 1.2208 | 39.22 | 2000 | 0.8962 | 0.6664 |
|
| 75 |
+
| 1.2145 | 41.18 | 2100 | 0.8903 | 0.6734 |
|
| 76 |
+
| 1.1888 | 43.14 | 2200 | 0.8883 | 0.6708 |
|
| 77 |
+
| 1.1933 | 45.1 | 2300 | 0.8928 | 0.6723 |
|
| 78 |
+
| 1.1838 | 47.06 | 2400 | 0.8868 | 0.6679 |
|
| 79 |
+
| 1.1634 | 49.02 | 2500 | 0.8886 | 0.6657 |
|
| 80 |
+
|
| 81 |
+
|
| 82 |
+
### Framework versions
|
| 83 |
+
|
| 84 |
+
- Transformers 4.17.0.dev0
|
| 85 |
+
- Pytorch 1.10.2+cu102
|
| 86 |
+
- Datasets 1.18.3
|
| 87 |
+
- Tokenizers 0.11.0
|