Add C++ and Python API for Kokoro TTS models. (#1715)

This commit is contained in:
Fangjun Kuang
2025-01-16 14:24:51 +08:00
committed by GitHub
parent 9efe26a646
commit ffc6b480a0
27 changed files with 1193 additions and 29 deletions

View File

@@ -11,7 +11,7 @@ while the model is still generating.
Usage:
Example (1/5)
Example (1/6)
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 (2/5)
Example (2/6)
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 (3/5)
Example (3/6)
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
@@ -53,7 +53,7 @@ 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 (4/5)
Example (4/6)
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
@@ -71,7 +71,7 @@ python3 ./python-api-examples/offline-tts-play.py \
--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。"
Example (5/5)
Example (5/6)
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-en_US-ljspeech.tar.bz2
tar xvf matcha-icefall-en_US-ljspeech.tar.bz2
@@ -88,6 +88,22 @@ python3 ./python-api-examples/offline-tts-play.py \
--num-threads=2 \
"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 (6/6)
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-en-v0_19.tar.bz2
tar xf kokoro-en-v0_19.tar.bz2
rm kokoro-en-v0_19.tar.bz2
python3 ./python-api-examples/offline-tts.py \
--debug=1 \
--kokoro-model=./kokoro-en-v0_19/model.onnx \
--kokoro-voices=./kokoro-en-v0_19/voices.bin \
--kokoro-tokens=./kokoro-en-v0_19/tokens.txt \
--kokoro-data-dir=./kokoro-en-v0_19/espeak-ng-data \
--num-threads=2 \
--sid=10 \
--output-filename="./kokoro-10.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."
You can find more models at
https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
@@ -202,6 +218,36 @@ def add_matcha_args(parser):
)
def add_kokoro_args(parser):
parser.add_argument(
"--kokoro-model",
type=str,
default="",
help="Path to model.onnx for kokoro",
)
parser.add_argument(
"--kokoro-voices",
type=str,
default="",
help="Path to voices.bin for kokoro",
)
parser.add_argument(
"--kokoro-tokens",
type=str,
default="",
help="Path to tokens.txt for kokoro",
)
parser.add_argument(
"--kokoro-data-dir",
type=str,
default="",
help="Path to the dict directory of espeak-ng.",
)
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
@@ -209,6 +255,7 @@ def get_args():
add_vits_args(parser)
add_matcha_args(parser)
add_kokoro_args(parser)
parser.add_argument(
"--tts-rule-fsts",
@@ -407,6 +454,12 @@ def main():
data_dir=args.matcha_data_dir,
dict_dir=args.matcha_dict_dir,
),
kokoro=sherpa_onnx.OfflineTtsKokoroModelConfig(
model=args.kokoro_model,
voices=args.kokoro_voices,
tokens=args.kokoro_tokens,
data_dir=args.kokoro_data_dir,
),
provider=args.provider,
debug=args.debug,
num_threads=args.num_threads,

View File

@@ -12,7 +12,7 @@ generated audio.
Usage:
Example (1/5)
Example (1/6)
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 (2/5)
Example (2/6)
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 (3/5)
Example (3/6)
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
@@ -54,7 +54,7 @@ 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 (4/5)
Example (4/6)
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
@@ -72,7 +72,7 @@ python3 ./python-api-examples/offline-tts.py \
--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。"
Example (5/5)
Example (5/6)
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/matcha-icefall-en_US-ljspeech.tar.bz2
tar xvf matcha-icefall-en_US-ljspeech.tar.bz2
@@ -89,6 +89,23 @@ python3 ./python-api-examples/offline-tts.py \
--num-threads=2 \
"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 (6/6)
curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-en-v0_19.tar.bz2
tar xf kokoro-en-v0_19.tar.bz2
rm kokoro-en-v0_19.tar.bz2
python3 ./python-api-examples/offline-tts.py \
--debug=1 \
--kokoro-model=./kokoro-en-v0_19/model.onnx \
--kokoro-voices=./kokoro-en-v0_19/voices.bin \
--kokoro-tokens=./kokoro-en-v0_19/tokens.txt \
--kokoro-data-dir=./kokoro-en-v0_19/espeak-ng-data \
--num-threads=2 \
--sid=10 \
--output-filename="./kokoro-10.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."
You can find more models at
https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models
@@ -188,6 +205,36 @@ def add_matcha_args(parser):
)
def add_kokoro_args(parser):
parser.add_argument(
"--kokoro-model",
type=str,
default="",
help="Path to model.onnx for kokoro",
)
parser.add_argument(
"--kokoro-voices",
type=str,
default="",
help="Path to voices.bin for kokoro",
)
parser.add_argument(
"--kokoro-tokens",
type=str,
default="",
help="Path to tokens.txt for kokoro",
)
parser.add_argument(
"--kokoro-data-dir",
type=str,
default="",
help="Path to the dict directory of espeak-ng.",
)
def get_args():
parser = argparse.ArgumentParser(
formatter_class=argparse.ArgumentDefaultsHelpFormatter
@@ -195,6 +242,7 @@ def get_args():
add_vits_args(parser)
add_matcha_args(parser)
add_kokoro_args(parser)
parser.add_argument(
"--tts-rule-fsts",
@@ -206,7 +254,7 @@ def get_args():
parser.add_argument(
"--max-num-sentences",
type=int,
default=2,
default=1,
help="""Max number of sentences in a batch to avoid OOM if the input
text is very long. Set it to -1 to process all the sentences in a
single batch. A smaller value does not mean it is slower compared
@@ -289,6 +337,12 @@ def main():
data_dir=args.matcha_data_dir,
dict_dir=args.matcha_dict_dir,
),
kokoro=sherpa_onnx.OfflineTtsKokoroModelConfig(
model=args.kokoro_model,
voices=args.kokoro_voices,
tokens=args.kokoro_tokens,
data_dir=args.kokoro_data_dir,
),
provider=args.provider,
debug=args.debug,
num_threads=args.num_threads,