coqui-ai
/
TTS
mirror of https://github.com/coqui-ai/TTS.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add use_gst to enable global style token

pull/10/head
Eren Golge 2019-09-24 16:24:58 +02:00
parent 98af061d2e
commit 5b6b1f354d
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
config.json
View File

@ -79,6 +79,7 @@
"phoneme_language": "en-us", // depending on your target language, pick one from https://github.com/bootphon/phonemizer#languages
"text_cleaner": "phoneme_cleaners",
"use_speaker_embedding": false, // use speaker embedding to enable multi-speaker learning.
"style_wav_for_test": null // path to style wav file to be used in TacotronGST inference.
"style_wav_for_test": null, // path to style wav file to be used in TacotronGST inference.
"use_gst": false // TACOTRON ONLY: use global style tokens
}

3
utils/generic_utils.py
View File

@ -253,13 +253,14 @@ def setup_model(num_chars, num_speakers, c):
print(" > Using model: {}".format(c.model))
MyModel = importlib.import_module('TTS.models.' + c.model.lower())
MyModel = getattr(MyModel, c.model)
if c.model.lower() in ["tacotron", "tacotrongst"]:
if c.model.lower() in "tacotron":
model = MyModel(
num_chars=num_chars,
num_speakers=num_speakers,
r=c.r,
linear_dim=1025,
mel_dim=80,
gst=c.use_gst,
memory_size=c.memory_size,
attn_win=c.windowing,
attn_norm=c.attention_norm,