diff --git a/conf/voxcpm_v2/voxcpm_finetune_all.yaml b/conf/voxcpm_v2/voxcpm_finetune_all.yaml new file mode 100644 index 0000000..9717290 --- /dev/null +++ b/conf/voxcpm_v2/voxcpm_finetune_all.yaml @@ -0,0 +1,21 @@ +pretrained_path: /path/to/VoxCPM2/ +train_manifest: /path/to/train.jsonl +val_manifest: null +sample_rate: 48000 +batch_size: 2 +grad_accum_steps: 8 # effective batch size = batch_size × grad_accum_steps = 16 +num_workers: 8 +num_iters: 1000 +log_interval: 10 +valid_interval: 500 +save_interval: 500 +learning_rate: 0.00001 +weight_decay: 0.01 +warmup_steps: 100 +max_steps: 1000 +max_batch_tokens: 8192 +save_path: /path/to/checkpoints/finetune_all +tensorboard: /path/to/logs/finetune_all +lambdas: + loss/diff: 1.0 + loss/stop: 1.0 diff --git a/conf/voxcpm_v2/voxcpm_finetune_lora.yaml b/conf/voxcpm_v2/voxcpm_finetune_lora.yaml new file mode 100644 index 0000000..f5d2d8a --- /dev/null +++ b/conf/voxcpm_v2/voxcpm_finetune_lora.yaml @@ -0,0 +1,36 @@ +pretrained_path: /path/to/VoxCPM2/ +train_manifest: /path/to/train.jsonl +val_manifest: null +sample_rate: 48000 +batch_size: 2 +grad_accum_steps: 8 # effective batch size = batch_size × grad_accum_steps = 16 +num_workers: 8 +num_iters: 1000 +log_interval: 10 +valid_interval: 500 +save_interval: 500 +learning_rate: 0.0001 +weight_decay: 0.01 +warmup_steps: 100 +max_steps: 1000 +max_batch_tokens: 8192 +save_path: /path/to/checkpoints/finetune_lora +tensorboard: /path/to/logs/finetune_lora +lambdas: + loss/diff: 1.0 + loss/stop: 1.0 + +# LoRA configuration +lora: + enable_lm: true + enable_dit: true + enable_proj: false + r: 32 + alpha: 32 + dropout: 0.0 + +# Distribution options (optional) +# - If distribute=false (default): save pretrained_path as base_model in lora_config.json +# - If distribute=true: save hf_model_id as base_model (hf_model_id is required) +# hf_model_id: "openbmb/VoxCPM2" +# distribute: true