Commit
•
37d4ba0
1
Parent(s):
c0e47e1
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: wav2vec2-burak-new-300-v2-3
|
| 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-burak-new-300-v2-3
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 0.2910
|
| 18 |
+
- Wer: 0.2712
|
| 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: 0.0001
|
| 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: 500
|
| 44 |
+
- num_epochs: 71
|
| 45 |
+
|
| 46 |
+
### Training results
|
| 47 |
+
|
| 48 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 49 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 50 |
+
| 7.5554 | 4.9 | 500 | 3.1912 | 1.0 |
|
| 51 |
+
| 3.1116 | 9.8 | 1000 | 2.5931 | 1.0 |
|
| 52 |
+
| 1.291 | 14.71 | 1500 | 0.4394 | 0.5575 |
|
| 53 |
+
| 0.6214 | 19.61 | 2000 | 0.3243 | 0.4370 |
|
| 54 |
+
| 0.4501 | 24.51 | 2500 | 0.2890 | 0.3517 |
|
| 55 |
+
| 0.3659 | 29.41 | 3000 | 0.2809 | 0.3310 |
|
| 56 |
+
| 0.3065 | 34.31 | 3500 | 0.2882 | 0.3076 |
|
| 57 |
+
| 0.2739 | 39.22 | 4000 | 0.2632 | 0.2870 |
|
| 58 |
+
| 0.2516 | 44.12 | 4500 | 0.2872 | 0.2897 |
|
| 59 |
+
| 0.2316 | 49.02 | 5000 | 0.2875 | 0.2767 |
|
| 60 |
+
| 0.2159 | 53.92 | 5500 | 0.2953 | 0.2746 |
|
| 61 |
+
| 0.1957 | 58.82 | 6000 | 0.2955 | 0.2787 |
|
| 62 |
+
| 0.1997 | 63.73 | 6500 | 0.2963 | 0.2822 |
|
| 63 |
+
| 0.1852 | 68.63 | 7000 | 0.2910 | 0.2712 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.22.2
|
| 69 |
+
- Pytorch 1.12.1+cu113
|
| 70 |
+
- Datasets 2.5.1
|
| 71 |
+
- Tokenizers 0.12.1
|