Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Use piper_phonemize as text tokenizer in vctk TTS recipe #1522

Merged
merged 14 commits into from
Mar 18, 2024
11 changes: 8 additions & 3 deletions egs/vctk/TTS/vits/export-onnx.py
Original file line number Diff line number Diff line change
Expand Up @@ -97,7 +97,7 @@ def add_meta_data(filename: str, meta_data: Dict[str, str]):
for key, value in meta_data.items():
meta = model.metadata_props.add()
meta.key = key
meta.value = value
meta.value = str(value)

onnx.save(model, filename)

Expand Down Expand Up @@ -212,10 +212,15 @@ def export_model_onnx(
)

meta_data = {
"model_type": "VITS",
"model_type": "vits",
"version": "1",
"model_author": "k2-fsa",
"comment": "VITS generator",
"comment": "icefall", # must be icefall for models from icefall
"language": "English",
"voice": "en-us", # Choose your language appropriately
"has_espeak": 1,
"n_speakers": 108,
"sample_rate": 22050, # Must match the real sample rate
JinZr marked this conversation as resolved.
Show resolved Hide resolved
}
logging.info(f"meta_data: {meta_data}")

Expand Down
Loading