Commit
•
b7895ae
1
Parent(s):
1784bf9
update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,8 +2,6 @@
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
-
metrics:
|
| 6 |
-
- wer
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-large-asr-th
|
| 9 |
results: []
|
|
@@ -14,11 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# wav2vec2-large-asr-th
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on
|
| 18 |
-
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 3.3264
|
| 20 |
-
- Wer: 1.0
|
| 21 |
-
- Cer: 0.9960
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -37,32 +31,16 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 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:
|
| 47 |
- training_steps: 2000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
-
### Training results
|
| 51 |
-
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 53 |
-
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 54 |
-
| 9.7192 | 1.09 | 200 | 10.1504 | 1.0 | 1.0000 |
|
| 55 |
-
| 3.6967 | 2.19 | 400 | 3.9101 | 1.0 | 1.0000 |
|
| 56 |
-
| 3.5978 | 3.28 | 600 | 3.8292 | 1.0 | 1.0000 |
|
| 57 |
-
| 3.5324 | 4.37 | 800 | 3.6538 | 1.0 | 1.0000 |
|
| 58 |
-
| 3.529 | 5.46 | 1000 | 3.5816 | 1.0 | 1.0000 |
|
| 59 |
-
| 3.5145 | 6.56 | 1200 | 3.5487 | 1.0 | 1.0000 |
|
| 60 |
-
| 3.4544 | 7.65 | 1400 | 3.4912 | 1.0 | 0.9999 |
|
| 61 |
-
| 3.3666 | 8.74 | 1600 | 3.3998 | 1.0 | 0.9974 |
|
| 62 |
-
| 3.2963 | 9.84 | 1800 | 3.3264 | 1.0 | 0.9960 |
|
| 63 |
-
| 3.2361 | 10.93 | 2000 | 3.2402 | 1.0001 | 0.9950 |
|
| 64 |
-
|
| 65 |
-
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.26.1
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: wav2vec2-large-asr-th
|
| 7 |
results: []
|
|
|
|
| 12 |
|
| 13 |
# wav2vec2-large-asr-th
|
| 14 |
|
| 15 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on an unknown dataset.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
|
|
| 31 |
### Training hyperparameters
|
| 32 |
|
| 33 |
The following hyperparameters were used during training:
|
| 34 |
+
- learning_rate: 1e-05
|
| 35 |
- train_batch_size: 16
|
| 36 |
- eval_batch_size: 16
|
| 37 |
- seed: 42
|
| 38 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
+
- lr_scheduler_warmup_steps: 200
|
| 41 |
- training_steps: 2000
|
| 42 |
- mixed_precision_training: Native AMP
|
| 43 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
### Framework versions
|
| 45 |
|
| 46 |
- Transformers 4.26.1
|