Commit ·
d1fb441
1
Parent(s): c3315be
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-15
|
| 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 |
+
# wav2vec2-15
|
| 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: 0.8623
|
| 18 |
+
- Wer: 0.8585
|
| 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: 1e-05
|
| 38 |
+
- train_batch_size: 32
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 400
|
| 44 |
+
- num_epochs: 30
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
+
| 9.6808 | 1.37 | 200 | 3.7154 | 1.0 |
|
| 51 |
+
| 3.0784 | 2.74 | 400 | 3.1542 | 1.0 |
|
| 52 |
+
| 2.8919 | 4.11 | 600 | 2.9918 | 1.0 |
|
| 53 |
+
| 2.8317 | 5.48 | 800 | 2.8971 | 1.0 |
|
| 54 |
+
| 2.7958 | 6.85 | 1000 | 2.8409 | 1.0 |
|
| 55 |
+
| 2.7699 | 8.22 | 1200 | 2.8278 | 1.0 |
|
| 56 |
+
| 2.6365 | 9.59 | 1400 | 2.4657 | 1.0 |
|
| 57 |
+
| 2.1096 | 10.96 | 1600 | 1.8358 | 0.9988 |
|
| 58 |
+
| 1.6485 | 12.33 | 1800 | 1.4525 | 0.9847 |
|
| 59 |
+
| 1.3967 | 13.7 | 2000 | 1.2467 | 0.9532 |
|
| 60 |
+
| 1.2492 | 15.07 | 2200 | 1.1261 | 0.9376 |
|
| 61 |
+
| 1.1543 | 16.44 | 2400 | 1.0654 | 0.9194 |
|
| 62 |
+
| 1.0863 | 17.81 | 2600 | 1.0136 | 0.9161 |
|
| 63 |
+
| 1.0275 | 19.18 | 2800 | 0.9601 | 0.8827 |
|
| 64 |
+
| 0.9854 | 20.55 | 3000 | 0.9435 | 0.8878 |
|
| 65 |
+
| 0.9528 | 21.92 | 3200 | 0.9170 | 0.8807 |
|
| 66 |
+
| 0.926 | 23.29 | 3400 | 0.9121 | 0.8783 |
|
| 67 |
+
| 0.9025 | 24.66 | 3600 | 0.8884 | 0.8646 |
|
| 68 |
+
| 0.8909 | 26.03 | 3800 | 0.8836 | 0.8690 |
|
| 69 |
+
| 0.8717 | 27.4 | 4000 | 0.8810 | 0.8646 |
|
| 70 |
+
| 0.8661 | 28.77 | 4200 | 0.8623 | 0.8585 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.19.2
|
| 76 |
+
- Pytorch 1.11.0+cu113
|
| 77 |
+
- Datasets 2.2.2
|
| 78 |
+
- Tokenizers 0.12.1
|