Instructions to use harshit345/xlsr-wav2vec-speech-emotion-recognition with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use harshit345/xlsr-wav2vec-speech-emotion-recognition with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="harshit345/xlsr-wav2vec-speech-emotion-recognition")# Load model directly from transformers import AutoProcessor, Wav2Vec2ForSpeechClassification processor = AutoProcessor.from_pretrained("harshit345/xlsr-wav2vec-speech-emotion-recognition") model = Wav2Vec2ForSpeechClassification.from_pretrained("harshit345/xlsr-wav2vec-speech-emotion-recognition") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 4.99, | |
| "eval_accuracy": 0.9008264541625977, | |
| "eval_loss": 0.3769935369491577, | |
| "eval_runtime": 72.4575, | |
| "eval_samples": 121, | |
| "eval_samples_per_second": 1.67, | |
| "eval_steps_per_second": 0.428, | |
| "train_loss": 0.7233316548665365, | |
| "train_runtime": 4793.1545, | |
| "train_samples": 483, | |
| "train_samples_per_second": 0.504, | |
| "train_steps_per_second": 0.063 | |
| } |