How does Wav2Vec do downstream classification on labeled data? In the paper they use a CTC algorithm for fine-tuning on labeled data, is this how it’s done when someone fine-tunes it on a downstream task as well?
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| How to change head in Hubert/Wav2Vec2 for downstream video classification | 0 | 271 | November 2, 2022 | |
| Finetune / retrain wav2vec2 encoder in self-supervised manner | 0 | 274 | March 8, 2022 | |
| Can someone give me a simple example on how to train Wav2Vec2 for audio frame classification? | 1 | 300 | January 7, 2025 | |
| Wav2Vec2 for Audio Emotion Classification | 6 | 8227 | May 26, 2021 | |
| Wav2vec For Music Applications (generation, captioning, instrument classification) | 2 | 1511 | July 3, 2021 |