Commit ·
2be61c7
1
Parent(s): 3607125
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-17
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# wav2vec2-17
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 3.1355
|
| 18 |
+
- Wer: 1.0
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0003
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- gradient_accumulation_steps: 8
|
| 42 |
+
- total_train_batch_size: 256
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 50
|
| 46 |
+
- num_epochs: 30
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
| 52 |
+
| 7.5865 | 1.38 | 25 | 3.4717 | 1.0 |
|
| 53 |
+
| 2.9762 | 2.77 | 50 | 3.1483 | 1.0 |
|
| 54 |
+
| 2.9265 | 4.16 | 75 | 3.1946 | 1.0 |
|
| 55 |
+
| 2.8813 | 5.55 | 100 | 3.0504 | 1.0 |
|
| 56 |
+
| 2.887 | 6.93 | 125 | 3.1358 | 1.0 |
|
| 57 |
+
| 2.9124 | 8.33 | 150 | 3.1653 | 1.0 |
|
| 58 |
+
| 2.8854 | 9.71 | 175 | 3.1243 | 1.0 |
|
| 59 |
+
| 2.91 | 11.11 | 200 | 3.0879 | 1.0 |
|
| 60 |
+
| 2.8868 | 12.49 | 225 | 3.1658 | 1.0 |
|
| 61 |
+
| 2.8827 | 13.88 | 250 | 3.1236 | 1.0 |
|
| 62 |
+
| 2.911 | 15.27 | 275 | 3.1206 | 1.0 |
|
| 63 |
+
| 2.8829 | 16.66 | 300 | 3.1171 | 1.0 |
|
| 64 |
+
| 2.9105 | 18.05 | 325 | 3.1127 | 1.0 |
|
| 65 |
+
| 2.8845 | 19.44 | 350 | 3.1377 | 1.0 |
|
| 66 |
+
| 2.8803 | 20.82 | 375 | 3.1157 | 1.0 |
|
| 67 |
+
| 2.9102 | 22.22 | 400 | 3.1265 | 1.0 |
|
| 68 |
+
| 2.8803 | 23.6 | 425 | 3.1493 | 1.0 |
|
| 69 |
+
| 2.8837 | 24.99 | 450 | 3.1085 | 1.0 |
|
| 70 |
+
| 2.9106 | 26.38 | 475 | 3.1099 | 1.0 |
|
| 71 |
+
| 2.8787 | 27.77 | 500 | 3.1352 | 1.0 |
|
| 72 |
+
| 2.9132 | 29.16 | 525 | 3.1355 | 1.0 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.19.2
|
| 78 |
+
- Pytorch 1.11.0+cu113
|
| 79 |
+
- Datasets 2.2.2
|
| 80 |
+
- Tokenizers 0.12.1
|