Hi I was reading the paper for wav2vec and they mention that for the first 10k updates only the output classifier is trained, after which the Transformer is also updated, how I can add this variable on the huggingface Trainer to follow the paper suggestion.
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
Wav2vec2 using transformers library | 0 | 278 | November 18, 2021 | |
Wav2Vec Classification on Labeled Data | 0 | 94 | February 28, 2024 | |
Need help on wav2vec 2.0 models training | 2 | 931 | July 31, 2021 | |
Wav2vec2 Acces Feature Layers Performance | 1 | 455 | May 7, 2025 | |
How to change head in Hubert/Wav2Vec2 for downstream video classification | 0 | 271 | November 2, 2022 |