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

Merge pull request #406 from mittimithai/patch-6 

small change for multispeaker
This commit is contained in:
Eren Gölge 2020-05-15 11:11:04 +02:00 committed by GitHub
parent 7292d303b9 25f466f299
commit 93cab61d80
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
server/synthesizer.py
View File

@ -164,16 +164,20 @@ class Synthesizer(object):
sentences = list(filter(None, [s.strip() for s in sentences])) # remove empty sentences sentences = list(filter(None, [s.strip() for s in sentences])) # remove empty sentences
return sentences return sentences
def tts(self, text): def tts(self, text, speaker_id=None):
wavs = [] wavs = []
sens = self.split_into_sentences(text) sens = self.split_into_sentences(text)
print(sens) print(sens)
speaker_id = id_to_torch(speaker_id)
if speaker_id is not None and self.use_cuda:
speaker_id = speaker_id.cuda()
for sen in sens: for sen in sens:
# preprocess the given text # preprocess the given text
inputs = text_to_seqvec(sen, self.tts_config, self.use_cuda) inputs = text_to_seqvec(sen, self.tts_config, self.use_cuda)
# synthesize voice # synthesize voice
decoder_output, postnet_output, alignments, _ = run_model( decoder_output, postnet_output, alignments, _ = run_model(
self.tts_model, inputs, self.tts_config, False, None, None) self.tts_model, inputs, self.tts_config, False, speaker_id, None)
# convert outputs to numpy # convert outputs to numpy
postnet_output, decoder_output, _ = parse_outputs( postnet_output, decoder_output, _ = parse_outputs(
postnet_output, decoder_output, alignments) postnet_output, decoder_output, alignments)