Instructions to use padmalcom/wav2vec2-large-emotion-detection-german with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use padmalcom/wav2vec2-large-emotion-detection-german with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="padmalcom/wav2vec2-large-emotion-detection-german")# Load model directly from transformers import AutoProcessor, Wav2Vec2ForSpeechClassification processor = AutoProcessor.from_pretrained("padmalcom/wav2vec2-large-emotion-detection-german") model = Wav2Vec2ForSpeechClassification.from_pretrained("padmalcom/wav2vec2-large-emotion-detection-german", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,7 @@ metrics:
|
|
| 19 |
- accuracy
|
| 20 |
---
|
| 21 |
This wav2vec2 based emotion detection model is trained on the [emo-DB dataset](http://emodb.bilderbar.info/start.html).
|
|
|
|
| 22 |
|
| 23 |
Emotion classes are:
|
| 24 |
- 0: 'anger'
|
|
|
|
| 19 |
- accuracy
|
| 20 |
---
|
| 21 |
This wav2vec2 based emotion detection model is trained on the [emo-DB dataset](http://emodb.bilderbar.info/start.html).
|
| 22 |
+
Code for training can be found [here](https://github.com/padmalcom/wav2vec2-emotion-detection-ger).
|
| 23 |
|
| 24 |
Emotion classes are:
|
| 25 |
- 0: 'anger'
|