Pine/VoxCPM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix VoxCPM2 training sample_rate: 48000 -> 16000 (match AudioVAE encoder)

Browse Source 
Made-with: Cursor
This commit is contained in:
刘鑫
2026-04-07 22:57:42 +08:00
parent da700f264e
commit 46cfce0c97
4 changed files with 53 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
conf/voxcpm_v2/voxcpm_finetune_all.yaml
+2 -1
View File
@@ -1,7 +1,8 @@
pretrained_path: /path/to/VoxCPM2/
train_manifest: /path/to/train.jsonl
val_manifest: null
sample_rate: 48000
sample_rate: 16000 # AudioVAE encoder input rate; must match audio_vae_config.sample_rate
out_sample_rate: 48000 # AudioVAE decoder output rate; only used at inference, not during training
batch_size: 2
grad_accum_steps: 8 # effective batch size = batch_size × grad_accum_steps = 16
num_workers: 8
conf/voxcpm_v2/voxcpm_finetune_lora.yaml
+2 -1
View File
@@ -1,7 +1,8 @@
pretrained_path: /path/to/VoxCPM2/
train_manifest: /path/to/train.jsonl
val_manifest: null
sample_rate: 48000
sample_rate: 16000 # AudioVAE encoder input rate; must match audio_vae_config.sample_rate
out_sample_rate: 48000 # AudioVAE decoder output rate; only used at inference, not during training
batch_size: 2
grad_accum_steps: 8 # effective batch size = batch_size × grad_accum_steps = 16
num_workers: 8