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

Synthesizer skips over embeddings file if model only has one speaker (#2587) 

* It looks like the Neon model is special in that t does not have a speaker_name and it wants to get the only item available. This was blocking a valid model with one speaker and a d_vector_file from being executed to get the embedding.

* Update synthesizer.py

oh my how embarrassing
fix_doc_dataset
Dusty Hagstrom 2023-10-16 02:55:45 -07:00 committed by GitHub
parent e4b8d71f2b
commit 13cd076a7f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
TTS/utils/synthesizer.py
View File

@ -299,11 +299,7 @@ class Synthesizer(nn.Module):
speaker_embedding = None
speaker_id = None
if self.tts_speakers_file or hasattr(self.tts_model.speaker_manager, "name_to_id"):
# handle Neon models with single speaker.
if len(self.tts_model.speaker_manager.name_to_id) == 1:
speaker_id = list(self.tts_model.speaker_manager.name_to_id.values())[0]
elif speaker_name and isinstance(speaker_name, str):
if speaker_name and isinstance(speaker_name, str):
if self.tts_config.use_d_vector_file:
# get the average speaker embedding from the saved d_vectors.
speaker_embedding = self.tts_model.speaker_manager.get_mean_embedding(
@ -313,7 +309,9 @@ class Synthesizer(nn.Module):
else:
# get speaker idx from the speaker name
speaker_id = self.tts_model.speaker_manager.name_to_id[speaker_name]
# handle Neon models with single speaker.
elif len(self.tts_model.speaker_manager.name_to_id) == 1:
speaker_id = list(self.tts_model.speaker_manager.name_to_id.values())[0]
elif not speaker_name and not speaker_wav:
raise ValueError(
" [!] Looks like you are using a multi-speaker model. "