You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
TianYuan
1f128a0817
Merge pull request #2117 from yt605155624/ernie_sat_trainer
[TTS]add ernie sat trainer
|
2 years ago |
| .. |
|
ernie_sat
|
updatte batch_fn train.py, test=doc
|
2 years ago |
|
fastspeech2
|
add blank between characters for vits, test=tts
|
2 years ago |
|
gan_vocoder
|
add blank between characters for vits, test=tts
|
2 years ago |
|
speedyspeech
|
add blank between characters for vits, test=tts
|
2 years ago |
|
tacotron2
|
add blank between characters for vits, test=tts
|
2 years ago |
|
transformer_tts
|
add blank between characters for vits, test=tts
|
2 years ago |
|
vits
|
add blank between characters for vits, test=tts
|
2 years ago |
|
waveflow
|
add blank between characters for vits, test=tts
|
2 years ago |
|
wavernn
|
add VITS readme, test=tts
|
2 years ago |
|
__init__.py
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
csmsc_test.txt
|
fix cr, test=tts
|
2 years ago |
|
inference.py
|
add onnx models for aishell3/ljspeech/vctk's tts3/voc1/voc5, test=tts
|
2 years ago |
|
inference_streaming.py
|
reneame chunk to block in streaming tts, test=tts
|
2 years ago |
|
ort_predict.py
|
add paddle device set for ort and inference, test=doc
|
2 years ago |
|
ort_predict_e2e.py
|
add onnx models for aishell3/ljspeech/vctk's tts3/voc1/voc5, test=tts
|
2 years ago |
|
ort_predict_streaming.py
|
reneame chunk to block in streaming tts, test=tts
|
2 years ago |
|
sentences.txt
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
sentences_en.txt
|
merge deepspeech, parakeet and text_processing into paddlespeech
|
3 years ago |
|
sentences_mix.txt
|
add mix tts, test=tts
|
2 years ago |
|
stream_play_tts.py
|
add stream_play_tts.py, test=doc
|
2 years ago |
|
syn_utils.py
|
Merge pull request #2117 from yt605155624/ernie_sat_trainer
|
2 years ago |
|
synthesize.py
|
fix #2013; and format
|
2 years ago |
|
synthesize_e2e.py
|
add mix frontend, test=tts
|
2 years ago |
|
synthesize_streaming.py
|
reneame chunk to block in streaming tts, test=tts
|
2 years ago |
|
voice_cloning.py
|
fix #2013; and format
|
2 years ago |
