bookbot/vits-base-sw-KE-OpenBible
By bookbot · ↓ 5 · ♥ 2 · Updated 2024-04-27
What's in this repo
This page lists the files in bookbot/vits-base-sw-KE-OpenBible, including vits-sw-KE-OpenBible.onnx.
- 1 ONNX models (.onnx files)
- 9 files, including 2 .pth, 1 .md, 1 .json, 1 .1, 1 .0, 1 .py
- Last updated 2024-04-27
ONNX files
| File | Size | Download |
|---|---|---|
| vits-sw-KE-OpenBible.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
VITS Base sw-KE-OpenBible
VITS Base sw-KE-OpenBible is an end-to-end text-to-speech model based on the VITS architecture. This model was trained from scratch on a real audio dataset. The list of real speakers include:
- sw-KE-OpenBible
The model's vocabulary contains the different IPA phonemes found in gruut.
This model was trained using VITS framework. All training was done on a Scaleway L40S VM with a NVIDIA L40S GPU. All necessary scripts used for training could be found in the Files and versions tab, as well as the Training metrics logged via Tensorboard.
Model
| Model | SR (Hz) | Mel range (Hz) | FFT / Hop / Win | #epochs |
|---|---|---|---|---|
| VITS Base sw-KE-OpenBible | 44.1K | 0-null | 2048 / 512 / 2048 | 12000 |
Training procedure
Prepare Data
python preprocess.py \
--text_index 1 \
--filelists filelists/sw-KE-OpenBible_text_train_filelist.txt filelists/sw-KE-OpenBible_text_val_filelist.txt \
--text_cleaners swahili_cleaners
Train
python train.py -c configs/sw_ke_openbible_base.json -m sw_ke_openbible_base
Frameworks
- PyTorch 2.2.2
- VITS
Model info
Created: 2024-04-27
Updated: 2024-04-27
View on Hugging Face