update model card README.md
Browse files
README.md
CHANGED
|
@@ -7,16 +7,6 @@ metrics:
|
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-base-finetune-vi-v2
|
| 9 |
results: []
|
| 10 |
-
widget:
|
| 11 |
-
- example_title: SOICT 2023 - SLU public test 1
|
| 12 |
-
src: >-
|
| 13 |
-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/055R7BruAa333g9teFfamQH.wav
|
| 14 |
-
- example_title: SOICT 2023 - SLU public test 2
|
| 15 |
-
src: >-
|
| 16 |
-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/0BLHhoJexE8THB8BrsZxWbh.wav
|
| 17 |
-
- example_title: SOICT 2023 - SLU public test 3
|
| 18 |
-
src: >-
|
| 19 |
-
https://huggingface.co/foxxy-hm/wav2vec2-base-finetune-vi/raw/main/audio-test/1ArUTGWJQ9YALH2xaNhU6GV.wav
|
| 20 |
---
|
| 21 |
|
| 22 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -26,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 26 |
|
| 27 |
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the None dataset.
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
-
- Loss:
|
| 30 |
-
- Wer:
|
| 31 |
|
| 32 |
## Model description
|
| 33 |
|
|
@@ -46,20 +36,23 @@ More information needed
|
|
| 46 |
### Training hyperparameters
|
| 47 |
|
| 48 |
The following hyperparameters were used during training:
|
| 49 |
-
- learning_rate:
|
| 50 |
- train_batch_size: 8
|
| 51 |
- eval_batch_size: 8
|
| 52 |
- seed: 42
|
| 53 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 54 |
- lr_scheduler_type: linear
|
| 55 |
- lr_scheduler_warmup_steps: 1000
|
| 56 |
-
- num_epochs:
|
| 57 |
|
| 58 |
### Training results
|
| 59 |
|
| 60 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer
|
| 61 |
-
|
| 62 |
-
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
|
|
|
| 7 |
model-index:
|
| 8 |
- name: wav2vec2-base-finetune-vi-v2
|
| 9 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [nguyenvulebinh/wav2vec2-base-vietnamese-250h](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vietnamese-250h) on the None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 4.6968
|
| 20 |
+
- Wer: 0.9698
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 36 |
### Training hyperparameters
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 3e-05
|
| 40 |
- train_batch_size: 8
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 1000
|
| 46 |
+
- num_epochs: 3
|
| 47 |
|
| 48 |
### Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 52 |
+
| 17.4813 | 0.67 | 500 | 5.4377 | 0.9996 |
|
| 53 |
+
| 5.4042 | 1.34 | 1000 | 5.0291 | 0.9996 |
|
| 54 |
+
| 4.836 | 2.0 | 1500 | 4.9688 | 0.9694 |
|
| 55 |
+
| 4.7651 | 2.67 | 2000 | 4.6968 | 0.9698 |
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|