Closed zrthxn closed 4 months ago
This fixes some issues with M4T finetuning CLI and enables freezing parts of a model before training
Example:
m4t_finetune \ --train_dataset gigaspeech/xs/xs_train_manifest.json \ --eval_dataset gigaspeech/xs/xs_validation_manifest.json \ --batch_size 10 \ --eval_steps 1000 \ --learning_rate 0.00008 \ --patience 10 \ --save_model_to checkpoints/expt5_m4tM.pt \ --model_name seamlessM4T_medium \ --freeze_layers \ model.speech_encoder_frontend \ model.speech_encoder \ model.text_encoder_frontend \ model.text_decoder.layers.0 \ model.text_decoder.layers.1 \ model.text_decoder.layers.2
This fixes some issues with M4T finetuning CLI and enables freezing parts of a model before training
Example: