Commit
•
090d7fc
1
Parent(s):
7e7f0ca
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- wer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: w2v2-libri
|
| 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 |
+
# w2v2-libri
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.7315
|
| 20 |
+
- Wer: 0.5574
|
| 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: 0.0001
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-07
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- lr_scheduler_warmup_steps: 500
|
| 46 |
+
- training_steps: 3000
|
| 47 |
+
- mixed_precision_training: Native AMP
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 7.1828 | 50.0 | 200 | 3.0563 | 1.0 |
|
| 54 |
+
| 2.8849 | 100.0 | 400 | 2.9023 | 1.0 |
|
| 55 |
+
| 1.5108 | 150.0 | 600 | 1.1468 | 0.6667 |
|
| 56 |
+
| 0.1372 | 200.0 | 800 | 1.3749 | 0.6279 |
|
| 57 |
+
| 0.0816 | 250.0 | 1000 | 1.3985 | 0.6224 |
|
| 58 |
+
| 0.0746 | 300.0 | 1200 | 1.5285 | 0.6141 |
|
| 59 |
+
| 0.0556 | 350.0 | 1400 | 1.5496 | 0.5920 |
|
| 60 |
+
| 0.0644 | 400.0 | 1600 | 1.6263 | 0.5947 |
|
| 61 |
+
| 0.0546 | 450.0 | 1800 | 1.6803 | 0.5906 |
|
| 62 |
+
| 0.0491 | 500.0 | 2000 | 1.6155 | 0.5837 |
|
| 63 |
+
| 0.0518 | 550.0 | 2200 | 1.6784 | 0.5698 |
|
| 64 |
+
| 0.0314 | 600.0 | 2400 | 1.6050 | 0.5602 |
|
| 65 |
+
| 0.0048 | 650.0 | 2600 | 1.7703 | 0.5546 |
|
| 66 |
+
| 0.0042 | 700.0 | 2800 | 1.7135 | 0.5615 |
|
| 67 |
+
| 0.0025 | 750.0 | 3000 | 1.7315 | 0.5574 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.25.1
|
| 73 |
+
- Pytorch 1.13.0+cu116
|
| 74 |
+
- Datasets 1.18.3
|
| 75 |
+
- Tokenizers 0.13.2
|