Update README.md
Browse files
README.md
CHANGED
|
@@ -13,6 +13,7 @@ library_name: transformers
|
|
| 13 |
license: cc-by-sa-4.0
|
| 14 |
metrics:
|
| 15 |
- accuracy
|
|
|
|
| 16 |
---
|
| 17 |
|
| 18 |
# Model Card
|
|
@@ -44,8 +45,16 @@ This model annotates primary stress in words on 20ms frames.
|
|
| 44 |
note = {Accepted at Interspeech 2025}
|
| 45 |
}
|
| 46 |
```
|
|
|
|
| 47 |
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Direct Use
|
| 50 |
|
| 51 |
The model is intended for data-driven analyses in primary stress position. At the moment, it has been proven to work on 4 datasets in 3 languages.
|
|
@@ -155,5 +164,4 @@ print(ds["primary_stress"][0])
|
|
| 155 |
|
| 156 |
## Evaluation
|
| 157 |
|
| 158 |
-
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 159 |
-
|
|
|
|
| 13 |
license: cc-by-sa-4.0
|
| 14 |
metrics:
|
| 15 |
- accuracy
|
| 16 |
+
pipeline_tag: audio-classification
|
| 17 |
---
|
| 18 |
|
| 19 |
# Model Card
|
|
|
|
| 45 |
note = {Accepted at Interspeech 2025}
|
| 46 |
}
|
| 47 |
```
|
| 48 |
+
### Evaluation results
|
| 49 |
|
| 50 |
|
| 51 |
+
|test language|accuracy|
|
| 52 |
+
| ---|---|
|
| 53 |
+
| Croatian| 99.1|
|
| 54 |
+
|Serbian|99.3|
|
| 55 |
+
|Chakavian (variant of Croatian)|88.9|
|
| 56 |
+
|Slovenian|89.0|
|
| 57 |
+
|
| 58 |
### Direct Use
|
| 59 |
|
| 60 |
The model is intended for data-driven analyses in primary stress position. At the moment, it has been proven to work on 4 datasets in 3 languages.
|
|
|
|
| 164 |
|
| 165 |
## Evaluation
|
| 166 |
|
| 167 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
|
|