Transformers
Safetensors
Slovenian
wav2vec2-bert
audio-frame-classification
prosody
segmentation
audio
speech
Instructions to use classla/wav2vecbert2-prosodicUnit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use classla/wav2vecbert2-prosodicUnit with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForAudioFrameClassification processor = AutoProcessor.from_pretrained("classla/wav2vecbert2-prosodicUnit") model = AutoModelForAudioFrameClassification.from_pretrained("classla/wav2vecbert2-prosodicUnit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -60,9 +60,9 @@ We evaluate the model indirectly, and only care about the positive class:
|
|
| 60 |
|
| 61 |
In this fashion we obtain the following metrics:
|
| 62 |
|
| 63 |
-
* Precision: 0.
|
| 64 |
-
* Recall: 0.
|
| 65 |
-
* F_1 score: 0.
|
| 66 |
|
| 67 |

|
|
|
|
| 60 |
|
| 61 |
In this fashion we obtain the following metrics:
|
| 62 |
|
| 63 |
+
* Precision: 0.9464
|
| 64 |
+
* Recall: 0.8260
|
| 65 |
+
* F_1 score: 0.8821
|
| 66 |
|
| 67 |

|