Commit
•
0816d69
1
Parent(s):
f67ac73
update model card README.md
Browse files
README.md
CHANGED
|
@@ -1,13 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: openai/whisper-small
|
| 3 |
-
datasets:
|
| 4 |
-
- JRHuy/vivos-fleurs
|
| 5 |
language:
|
| 6 |
- vi
|
| 7 |
-
library_name: peft
|
| 8 |
license: apache-2.0
|
| 9 |
tags:
|
| 10 |
- generated_from_trainer
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: Whisper Small Vietnamese - Steve Hoang
|
| 13 |
results: []
|
|
@@ -20,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 20 |
|
| 21 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Vietnamese ASR dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 1.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -39,7 +37,7 @@ More information needed
|
|
| 39 |
### Training hyperparameters
|
| 40 |
|
| 41 |
The following hyperparameters were used during training:
|
| 42 |
-
- learning_rate:
|
| 43 |
- train_batch_size: 16
|
| 44 |
- eval_batch_size: 16
|
| 45 |
- seed: 42
|
|
@@ -52,15 +50,14 @@ The following hyperparameters were used during training:
|
|
| 52 |
|
| 53 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
-
| 2.
|
| 56 |
-
|
|
| 57 |
-
| 1.
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
| 61 |
|
| 62 |
-
- PEFT 0.11.2.dev0
|
| 63 |
- Transformers 4.30.0
|
| 64 |
- Pytorch 2.1.2
|
| 65 |
- Datasets 2.20.0
|
| 66 |
-
- Tokenizers 0.13.3
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
- vi
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- JRHuy/vivos-fleurs
|
| 9 |
model-index:
|
| 10 |
- name: Whisper Small Vietnamese - Steve Hoang
|
| 11 |
results: []
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Vietnamese ASR dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 1.3438
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1.25e-05
|
| 41 |
- train_batch_size: 16
|
| 42 |
- eval_batch_size: 16
|
| 43 |
- seed: 42
|
|
|
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:-----:|:----:|:---------------:|
|
| 53 |
+
| 2.4238 | 0.11 | 100 | 2.2401 |
|
| 54 |
+
| 1.8787 | 0.21 | 200 | 1.7789 |
|
| 55 |
+
| 1.3912 | 0.32 | 300 | 1.3438 |
|
| 56 |
|
| 57 |
|
| 58 |
### Framework versions
|
| 59 |
|
|
|
|
| 60 |
- Transformers 4.30.0
|
| 61 |
- Pytorch 2.1.2
|
| 62 |
- Datasets 2.20.0
|
| 63 |
+
- Tokenizers 0.13.3
|