Downloads · 30 days
0
neutts-nano-te-1
vanshnawander/neutts-nano-te-1
neutts-nano-te-1 is a machine learning model from vanshnawander. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Fine-tuned on Telugu speech data for text-to-speech synthesis with voice cloning.
Access
Public
Updated Feb 10, 2026
Repo size
3.7 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt2.3 GB · 60%
At a glance
- Access
- Public
- Created
- Feb 10, 2026
- Updated
- Feb 10, 2026
- SHA
- c7673506
Model card
From the Hugging Face model README
NeuTTS-Nano Telugu Checkpoint
Fine-tuned on Telugu speech data for text-to-speech synthesis with voice cloning.
Datasets
data/encoded_te_indictts
Training
| Param | Value |
|---|---|
| Base model | neuphonic/neutts-nano |
| Max steps | -1 |
| Learning rate | 3e-05 |
| Batch size | 1 |
| Precision | bf16 |
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("vanshnawander/neutts-nano-te-1", subfolder="final")
tokenizer = AutoTokenizer.from_pretrained("vanshnawander/neutts-nano-te-1", subfolder="final")
Structure
best/— lowest eval loss checkpoint (always kept)final/— last training step (always kept)checkpoint-<step>/— rolling window of last 5 checkpoints
Auto-generated by HFSyncCallback — 2026-02-10 22:58
- Created
- Feb 10, 2026
- Updated
- Feb 10, 2026