Commit ·
1d7e011
1
Parent(s): 3ec46ae
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-8
|
| 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 |
+
# wav2vec2-8
|
| 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: 3.1169
|
| 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: 0.0006
|
| 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 |
+
| 3.9398 | 1.56 | 200 | 3.1250 | 1.0 |
|
| 51 |
+
| 2.8703 | 3.12 | 400 | 3.1608 | 1.0 |
|
| 52 |
+
| 2.8632 | 4.69 | 600 | 3.1329 | 1.0 |
|
| 53 |
+
| 2.8638 | 6.25 | 800 | 3.0795 | 1.0 |
|
| 54 |
+
| 2.8595 | 7.81 | 1000 | 3.1410 | 1.0 |
|
| 55 |
+
| 2.8611 | 9.38 | 1200 | 3.0952 | 1.0 |
|
| 56 |
+
| 2.861 | 10.94 | 1400 | 3.1391 | 1.0 |
|
| 57 |
+
| 2.8603 | 12.5 | 1600 | 3.0639 | 1.0 |
|
| 58 |
+
| 2.8568 | 14.06 | 1800 | 3.1180 | 1.0 |
|
| 59 |
+
| 2.8563 | 15.62 | 2000 | 3.1170 | 1.0 |
|
| 60 |
+
| 2.857 | 17.19 | 2200 | 3.0846 | 1.0 |
|
| 61 |
+
| 2.8574 | 18.75 | 2400 | 3.0740 | 1.0 |
|
| 62 |
+
| 2.8543 | 20.31 | 2600 | 3.1482 | 1.0 |
|
| 63 |
+
| 2.8567 | 21.88 | 2800 | 3.1604 | 1.0 |
|
| 64 |
+
| 2.8561 | 23.44 | 3000 | 3.1055 | 1.0 |
|
| 65 |
+
| 2.858 | 25.0 | 3200 | 3.0669 | 1.0 |
|
| 66 |
+
| 2.8524 | 26.56 | 3400 | 3.0992 | 1.0 |
|
| 67 |
+
| 2.8557 | 28.12 | 3600 | 3.1050 | 1.0 |
|
| 68 |
+
| 2.8527 | 29.69 | 3800 | 3.1169 | 1.0 |
|
| 69 |
+
|
| 70 |
+
|
| 71 |
+
### Framework versions
|
| 72 |
+
|
| 73 |
+
- Transformers 4.19.2
|
| 74 |
+
- Pytorch 1.11.0+cu113
|
| 75 |
+
- Datasets 2.2.2
|
| 76 |
+
- Tokenizers 0.12.1
|