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 | |
---|---|---|---|---|
Is there any tutorial 4 pretrain wav2vec2 | 4 | 918 | November 6, 2024 | |
Train phoneme recognizer using Wav2Vec2 intermediate features | 0 | 491 | November 1, 2022 | |
Wav2vec2 using transformers library | 0 | 274 | November 18, 2021 | |
Pre-training for Wav2Vec2-XLSR via Huggingface | 15 | 5284 | November 5, 2024 | |
How to convert wav2vec2 checkpoint to Huggingface processor and model? | 1 | 564 | July 25, 2021 |