Update README.md
Browse files
README.md
CHANGED
|
@@ -24,7 +24,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 24 |
|
| 25 |
# punct_restore_fr
|
| 26 |
|
| 27 |
-
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on a raw opensubtitles dataset.
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
- Loss: 0.0301
|
| 30 |
- Precision: 0.9601
|
|
@@ -34,12 +34,12 @@ It achieves the following results on the evaluation set:
|
|
| 34 |
|
| 35 |
## Model description
|
| 36 |
|
| 37 |
-
Classifies tokens based on beginning of
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
-
This model aims to help punctuation restoration on French YouTube auto-generated subtitles.
|
| 42 |
-
|
| 43 |
## Training and evaluation data
|
| 44 |
|
| 45 |
1 million Open Subtitles (French) sentences. 80%/10%/10% training/validation/test split.
|
|
|
|
| 24 |
|
| 25 |
# punct_restore_fr
|
| 26 |
|
| 27 |
+
This model is a fine-tuned version of [camembert-base](https://huggingface.co/camembert-base) on a raw, French opensubtitles dataset.
|
| 28 |
It achieves the following results on the evaluation set:
|
| 29 |
- Loss: 0.0301
|
| 30 |
- Precision: 0.9601
|
|
|
|
| 34 |
|
| 35 |
## Model description
|
| 36 |
|
| 37 |
+
Classifies tokens based on beginning of French sentences (B-SENT) and everything else (O).
|
| 38 |
|
| 39 |
## Intended uses & limitations
|
| 40 |
|
| 41 |
+
This model aims to help punctuation restoration on French YouTube auto-generated subtitles. In doing so, one can measure more in a corpus such as words per sentence, grammar structures per sentence, etc.
|
| 42 |
+
|
| 43 |
## Training and evaluation data
|
| 44 |
|
| 45 |
1 million Open Subtitles (French) sentences. 80%/10%/10% training/validation/test split.
|