Text-to-Speech
Transformers
Japanese
style-bert-vits2
style-bert-vits2-jp-extra
tts
childish
childish voice
japanese
text2audio
text-to-audio
text to audio
audio
Instructions to use RikkaBotan/style_bert_vits2_jp_extra_sweet_original with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RikkaBotan/style_bert_vits2_jp_extra_sweet_original with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="RikkaBotan/style_bert_vits2_jp_extra_sweet_original")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("RikkaBotan/style_bert_vits2_jp_extra_sweet_original", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Upload 2 files
Browse files- config.json +5 -5
- style_vectors.npy +1 -1
config.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"model_name": "
|
| 3 |
"train": {
|
| 4 |
"log_interval": 200,
|
| 5 |
-
"eval_interval":
|
| 6 |
"seed": 42,
|
| 7 |
"epochs": 100,
|
| 8 |
"learning_rate": 0.0001,
|
|
@@ -31,8 +31,8 @@
|
|
| 31 |
},
|
| 32 |
"data": {
|
| 33 |
"use_jp_extra": true,
|
| 34 |
-
"training_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/
|
| 35 |
-
"validation_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/
|
| 36 |
"max_wav_value": 32768.0,
|
| 37 |
"sampling_rate": 44100,
|
| 38 |
"filter_length": 2048,
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"n_speakers": 1,
|
| 46 |
"cleaned_text": true,
|
| 47 |
"spk2id": {
|
| 48 |
-
"
|
| 49 |
},
|
| 50 |
"num_styles": 1,
|
| 51 |
"style2id": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"model_name": "rikka_botan3",
|
| 3 |
"train": {
|
| 4 |
"log_interval": 200,
|
| 5 |
+
"eval_interval": 450,
|
| 6 |
"seed": 42,
|
| 7 |
"epochs": 100,
|
| 8 |
"learning_rate": 0.0001,
|
|
|
|
| 31 |
},
|
| 32 |
"data": {
|
| 33 |
"use_jp_extra": true,
|
| 34 |
+
"training_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/rikka_botan3/train.list",
|
| 35 |
+
"validation_files": "/content/drive/MyDrive/Style-Bert-VITS2/Data/rikka_botan3/val.list",
|
| 36 |
"max_wav_value": 32768.0,
|
| 37 |
"sampling_rate": 44100,
|
| 38 |
"filter_length": 2048,
|
|
|
|
| 45 |
"n_speakers": 1,
|
| 46 |
"cleaned_text": true,
|
| 47 |
"spk2id": {
|
| 48 |
+
"rikka_botan3": 0
|
| 49 |
},
|
| 50 |
"num_styles": 1,
|
| 51 |
"style2id": {
|
style_vectors.npy
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1152
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5076dd060cea4a728534e8a418c0870c3cd52f2d357f48b08970bef79735d031
|
| 3 |
size 1152
|