End of training
Browse files
README.md
CHANGED
|
@@ -15,24 +15,18 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# jp-speech-classifier
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3) on an
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.1895
|
| 21 |
- Accuracy: 0.7053
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
-
|
| 30 |
-
|
| 31 |
-
## Training and evaluation data
|
| 32 |
-
|
| 33 |
-
More information needed
|
| 34 |
-
|
| 35 |
-
## Training procedure
|
| 36 |
|
| 37 |
### Training hyperparameters
|
| 38 |
|
|
|
|
| 15 |
|
| 16 |
# jp-speech-classifier
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [cl-tohoku/bert-base-japanese-v3](https://huggingface.co/cl-tohoku/bert-base-japanese-v3) on an speech category dataset I have created myself.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 1.1895
|
| 21 |
- Accuracy: 0.7053
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
+
This model classifies Japanese sentences into factual, question, descriptive, opinion based or other sentences.
|
| 26 |
|
| 27 |
## Intended uses & limitations
|
| 28 |
|
| 29 |
+
I created this model to be used for my project attempting to quantitatively analyze political stances of Japanese politicians.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
|
| 31 |
### Training hyperparameters
|
| 32 |
|