EngineX-Iluvatar/enginex-mr_series-sherpa-onnx
Archived
15
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

Add C++ runtime for Matcha-TTS (#1627)

Browse Source
This commit is contained in:
Fangjun Kuang
2024-12-31 12:44:14 +08:00
committed by GitHub
parent 5c2cc48f50
commit 2c2926af7d
33 changed files with 1397 additions and 86 deletions
Download Patch File Download Diff File Expand all files Collapse all files

93
python-api-examples/offline-tts-play.py
View File

@@ -11,7 +11,7 @@ while the model is still generating.
Usage:
Example (1/3)
Example (1/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
tar xf vits-piper-en_US-amy-low.tar.bz2
@@ -23,7 +23,7 @@ python3 ./python-api-examples/offline-tts-play.py \
--output-filename=./generated.wav \
"Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar."
Example (2/3)
Example (2/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-zh-aishell3.tar.bz2
tar xvf vits-zh-aishell3.tar.bz2
@@ -37,7 +37,7 @@ python3 ./python-api-examples/offline-tts-play.py \
--output-filename=./liubei-21.wav \
"勿以恶小而为之，勿以善小而不为。惟贤惟德，能服于人。122334"
Example (3/3)
Example (3/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/sherpa-onnx-vits-zh-ll.tar.bz2
tar xvf sherpa-onnx-vits-zh-ll.tar.bz2
@@ -53,6 +53,24 @@ python3 ./python-api-examples/offline-tts-play.py \
--output-filename=./test-2.wav \
"当夜幕降临，星光点点，伴随着微风拂面，我在静谧中感受着时光的流转，思念如涟漪荡漾，梦境如画卷展开，我与自然融为一体，沉静在这片宁静的美丽之中，感受着生命的奇迹与温柔。2024年5月11号，拨打110或者18920240511。123456块钱。"
Example (4/4)
curl -O -SL https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-zh-baker.tar.bz2
tar xvf matcha-icefall-zh-baker.tar.bz2
rm matcha-icefall-zh-baker.tar.bz2
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
python3 ./python-api-examples/offline-tts-play.py \
--matcha-acoustic-model=./matcha-icefall-zh-baker/model-steps-3.onnx \
--matcha-vocoder=./hifigan_v2.onnx \
--matcha-lexicon=./matcha-icefall-zh-baker/lexicon.txt \
--matcha-tokens=./matcha-icefall-zh-baker/tokens.txt \
--tts-rule-fsts=./matcha-icefall-zh-baker/phone.fst,./matcha-icefall-zh-baker/date.fst,./matcha-icefall-zh-baker/number.fst \
--matcha-dict-dir=./matcha-icefall-zh-baker/dict \
--output-filename=./test-matcha.wav \
"某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。2024年12月31号，拨打110或者18920240511。123456块钱。"
You can find more models at
https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
@@ -84,14 +102,11 @@ except ImportError:
sys.exit(-1)
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
def add_vits_args(parser):
parser.add_argument(
"--vits-model",
type=str,
default="",
help="Path to vits model.onnx",
)
@@ -124,6 +139,60 @@ def get_args():
help="Path to the dict directory for models using jieba",
)
def add_matcha_args(parser):
parser.add_argument(
"--matcha-acoustic-model",
type=str,
default="",
help="Path to model.onnx for matcha",
)
parser.add_argument(
"--matcha-vocoder",
type=str,
default="",
help="Path to vocoder for matcha",
)
parser.add_argument(
"--matcha-lexicon",
type=str,
default="",
help="Path to lexicon.txt for matcha",
)
parser.add_argument(
"--matcha-tokens",
type=str,
default="",
help="Path to tokens.txt for matcha",
)
parser.add_argument(
"--matcha-data-dir",
type=str,
default="",
help="""Path to the dict directory of espeak-ng. If it is specified,
--matcha-lexicon and --matcha-tokens are ignored""",
)
parser.add_argument(
"--matcha-dict-dir",
type=str,
default="",
help="Path to the dict directory for models using jieba",
)
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
add_vits_args(parser)
add_matcha_args(parser)
parser.add_argument(
"--tts-rule-fsts",
type=str,
@@ -313,6 +382,14 @@ def main():
dict_dir=args.vits_dict_dir,
tokens=args.vits_tokens,
),
matcha=sherpa_onnx.OfflineTtsMatchaModelConfig(
acoustic_model=args.matcha_acoustic_model,
vocoder=args.matcha_vocoder,
lexicon=args.matcha_lexicon,
tokens=args.matcha_tokens,
data_dir=args.matcha_data_dir,
dict_dir=args.matcha_dict_dir,
),
provider=args.provider,
debug=args.debug,
num_threads=args.num_threads,

92
python-api-examples/offline-tts.py
View File

@@ -12,7 +12,7 @@ generated audio.
Usage:
Example (1/3)
Example (1/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-piper-en_US-amy-low.tar.bz2
tar xf vits-piper-en_US-amy-low.tar.bz2
@@ -24,7 +24,7 @@ python3 ./python-api-examples/offline-tts.py \
--output-filename=./generated.wav \
"Today as always, men fall into two groups: slaves and free men. Whoever does not have two-thirds of his day for himself, is a slave, whatever he may be: a statesman, a businessman, an official, or a scholar."
Example (2/3)
Example (2/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-icefall-zh-aishell3.tar.bz2
tar xvf vits-icefall-zh-aishell3.tar.bz2
@@ -38,7 +38,7 @@ python3 ./python-api-examples/offline-tts.py \
--output-filename=./liubei-21.wav \
"勿以恶小而为之，勿以善小而不为。惟贤惟德，能服于人。122334"
Example (3/3)
Example (3/4)
wget https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/sherpa-onnx-vits-zh-ll.tar.bz2
tar xvf sherpa-onnx-vits-zh-ll.tar.bz2
@@ -54,6 +54,23 @@ python3 ./python-api-examples/offline-tts.py \
--output-filename=./test-2.wav \
"当夜幕降临，星光点点，伴随着微风拂面，我在静谧中感受着时光的流转，思念如涟漪荡漾，梦境如画卷展开，我与自然融为一体，沉静在这片宁静的美丽之中，感受着生命的奇迹与温柔。2024年5月11号，拨打110或者18920240511。123456块钱。"
Example (4/4)
curl -O -SL https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-zh-baker.tar.bz2
tar xvf matcha-icefall-zh-baker.tar.bz2
rm matcha-icefall-zh-baker.tar.bz2
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/vocoder-models/hifigan_v2.onnx
python3 ./python-api-examples/offline-tts.py \
--matcha-acoustic-model=./matcha-icefall-zh-baker/model-steps-3.onnx \
--matcha-vocoder=./hifigan_v2.onnx \
--matcha-lexicon=./matcha-icefall-zh-baker/lexicon.txt \
--matcha-tokens=./matcha-icefall-zh-baker/tokens.txt \
--tts-rule-fsts=./matcha-icefall-zh-baker/phone.fst,./matcha-icefall-zh-baker/date.fst,./matcha-icefall-zh-baker/number.fst \
--matcha-dict-dir=./matcha-icefall-zh-baker/dict \
--output-filename=./test-matcha.wav \
"某某银行的副行长和一些行政领导表示，他们去过长江和长白山; 经济不断增长。2024年12月31号，拨打110或者18920240511。123456块钱。"
You can find more models at
https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
@@ -71,14 +88,11 @@ import sherpa_onnx
import soundfile as sf
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
def add_vits_args(parser):
parser.add_argument(
"--vits-model",
type=str,
default="",
help="Path to vits model.onnx",
)
@@ -111,6 +125,60 @@ def get_args():
help="Path to the dict directory for models using jieba",
)
def add_matcha_args(parser):
parser.add_argument(
"--matcha-acoustic-model",
type=str,
default="",
help="Path to model.onnx for matcha",
)
parser.add_argument(
"--matcha-vocoder",
type=str,
default="",
help="Path to vocoder for matcha",
)
parser.add_argument(
"--matcha-lexicon",
type=str,
default="",
help="Path to lexicon.txt for matcha",
)
parser.add_argument(
"--matcha-tokens",
type=str,
default="",
help="Path to tokens.txt for matcha",
)
parser.add_argument(
"--matcha-data-dir",
type=str,
default="",
help="""Path to the dict directory of espeak-ng. If it is specified,
--matcha-lexicon and --matcha-tokens are ignored""",
)
parser.add_argument(
"--matcha-dict-dir",
type=str,
default="",
help="Path to the dict directory for models using jieba",
)
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
)
add_vits_args(parser)
add_matcha_args(parser)
parser.add_argument(
"--tts-rule-fsts",
type=str,
@@ -196,6 +264,14 @@ def main():
dict_dir=args.vits_dict_dir,
tokens=args.vits_tokens,
),
matcha=sherpa_onnx.OfflineTtsMatchaModelConfig(
acoustic_model=args.matcha_acoustic_model,
vocoder=args.matcha_vocoder,
lexicon=args.matcha_lexicon,
tokens=args.matcha_tokens,
data_dir=args.matcha_data_dir,
dict_dir=args.matcha_dict_dir,
),
provider=args.provider,
debug=args.debug,
num_threads=args.num_threads,