End of training
Browse files
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
base_model: facebook/wav2vec2-xls-r-300m
|
| 6 |
datasets:
|
| 7 |
- make_dataset
|
| 8 |
model-index:
|
|
@@ -16,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
# wav2vec2-large-xls-r-300m-korean-g
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the make_dataset dataset.
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
@@ -35,17 +38,20 @@ More information needed
|
|
| 35 |
|
| 36 |
The following hyperparameters were used during training:
|
| 37 |
- learning_rate: 0.0001
|
| 38 |
-
- train_batch_size:
|
| 39 |
- eval_batch_size: 16
|
| 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: 1000
|
| 44 |
-
- num_epochs:
|
| 45 |
- mixed_precision_training: Native AMP
|
| 46 |
|
| 47 |
### Training results
|
| 48 |
|
|
|
|
|
|
|
|
|
|
| 49 |
|
| 50 |
|
| 51 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: facebook/wav2vec2-xls-r-300m
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
| 6 |
datasets:
|
| 7 |
- make_dataset
|
| 8 |
model-index:
|
|
|
|
| 16 |
# wav2vec2-large-xls-r-300m-korean-g
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the make_dataset dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 56.5813
|
| 21 |
+
- Cer: 1.0875
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
- learning_rate: 0.0001
|
| 41 |
+
- train_batch_size: 16
|
| 42 |
- eval_batch_size: 16
|
| 43 |
- seed: 42
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 1000
|
| 47 |
+
- num_epochs: 500
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | Cer |
|
| 53 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 19.3717 | 500.0 | 500 | 56.5813 | 1.0875 |
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|