You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

LoRA finetuning

Clone voice https://www.youtube.com/@MapaloMakhu

Tested with temperature 0.5

Config

model_name: "/workspace/outputs/finetune_no_unsloth/from_pretrained/SA_female/merged/" 

# Training Args
lora_rank: 16
lora_alpha: 64
epochs: 3
batch_size: 2
number_processes: 1
pad_token: 128263
learning_rate: 2.0e-4
save_steps: 10000

# Naming and paths
save_folder: "/workspace/outputs/finetune_no_unsloth/from_pretrained"
project_name: "mapalo_from_SA_female_pretrained"

dataset_name: vietnhat/speech-mapalo-dataset
dataset_ratio: 1
use_speaker_tag: false
Downloads last month
-
Safetensors
Model size
3.78B params
Tensor type
BF16
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support