Commit
•
18e03ac
1
Parent(s):
ed3ad6a
End of training
Browse files- README.md +67 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: wav2vec2-large-xls-r-korean
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# wav2vec2-large-xls-r-korean
|
| 15 |
+
|
| 16 |
+
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.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.5006
|
| 19 |
+
- Cer: 0.1178
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.0001
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 43 |
+
- lr_scheduler_type: linear
|
| 44 |
+
- lr_scheduler_warmup_steps: 1000
|
| 45 |
+
- num_epochs: 10
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 51 |
+
| 3.3321 | 1.11 | 300 | 3.8704 | 1.0 |
|
| 52 |
+
| 1.6999 | 2.22 | 600 | 1.8098 | 0.3638 |
|
| 53 |
+
| 0.6728 | 3.33 | 900 | 0.7710 | 0.1967 |
|
| 54 |
+
| 0.4398 | 4.44 | 1200 | 0.5838 | 0.1568 |
|
| 55 |
+
| 0.3202 | 5.56 | 1500 | 0.5421 | 0.1468 |
|
| 56 |
+
| 0.2286 | 6.67 | 1800 | 0.4912 | 0.1312 |
|
| 57 |
+
| 0.161 | 7.78 | 2100 | 0.4931 | 0.1247 |
|
| 58 |
+
| 0.1436 | 8.89 | 2400 | 0.4953 | 0.1211 |
|
| 59 |
+
| 0.1213 | 10.0 | 2700 | 0.5006 | 0.1178 |
|
| 60 |
+
|
| 61 |
+
|
| 62 |
+
### Framework versions
|
| 63 |
+
|
| 64 |
+
- Transformers 4.33.2
|
| 65 |
+
- Pytorch 1.12.1+cu113
|
| 66 |
+
- Datasets 2.14.5
|
| 67 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262107825
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54ff6ee5af3fb57f14f94119258a1a407930c398fba651bb82842fdbd94155e1
|
| 3 |
size 1262107825
|