You can deploy this model and start earning money today!

9FA/
baharani_v12_lora

Name: baharani_v12_lora
Availability: InStock

Views

No views yet

Baharani v12 VoxCPM2 LoRA

Param	Value
LoRA rank	64
LoRA alpha	128 (ratio 2.0)
LoRA dropout	0.0 (implicit regularization from rank constraint)
Learning rate	5e-5
Scheduler	Cosine with 1000-step warmup
Steps	15000 (~3.1 epochs)
Batch size	4 × 4 grad_accum = 16 effective
EMA decay	0.999
Validation	Every 3000 steps, best checkpoint selected

LoRA rank 64/alpha=128 (was r=32/alpha=32): more capacity for dialect features
Dropout removed: 68h of data provides natural regularization; dropout hurts audio quality
3.1 epochs (was ~1 epoch): proper convergence without underfitting
Cosine LR: smooth decay instead of constant → better convergence
EMA decay=0.999: appropriate halflife for 15K training steps
Train/val split: best checkpoint selection by validation loss
Lower LR (5e-5 vs 1e-4): finer adaptation without catastrophic forgetting

For EMA weights (recommended for production):

Apache 2.0