Add Python API for KittenTTS. (#2466)

@@ -328,6 +328,25 @@ log "Offline TTS test"
 # test waves are saved in ./tts
 mkdir ./tts
 
+log "test kitten tts"
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+python3 ./python-api-examples/offline-tts.py \
+  --debug=1 \
+  --kitten-model=./kitten-nano-en-v0_1-fp16/model.fp16.onnx \
+  --kitten-voices=./kitten-nano-en-v0_1-fp16/voices.bin \
+  --kitten-tokens=./kitten-nano-en-v0_1-fp16/tokens.txt \
+  --kitten-data-dir=./kitten-nano-en-v0_1-fp16/espeak-ng-data \
+  --num-threads=2 \
+  --sid=0 \
+  --output-filename="./tts/kitten-0.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."
+
+rm -rf kitten-nano-en-v0_1-fp16
+
 log "kokoro-multi-lang-v1_0 test"
 
 curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kokoro-multi-lang-v1_0.tar.bz2

@@ -11,7 +11,7 @@ while the model is still generating.
 
 Usage:
 
-Example (1/7)
+Example (1/8)
 
 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 (2/7)
+Example (2/8)
 
 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 (3/7)
+Example (3/8)
 
 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 (4/7)
+Example (4/8)
 
 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 (5/7)
+Example (5/8)
 
 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
@@ -88,7 +88,7 @@ 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 (6/7)
+Example (6/8)
 
 (This version of kokoro supports only English)
 
@@ -105,9 +105,9 @@ python3 ./python-api-examples/offline-tts.py \
   --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."
+  "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 (7/7)
+Example (7/8)
 
 (This version of kokoro supports English, Chinese, etc.)
 
@@ -128,6 +128,23 @@ python3 ./python-api-examples/offline-tts-play.py \
   --output-filename="./kokoro-18-zh-en.wav" \
   "中英文语音合成测试。This is generated by next generation Kaldi using Kokoro without Misaki. 你觉得中英文说的如何呢？"
 
+Example (8/8)
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+python3 ./python-api-examples/offline-tts-play.py \
+  --debug=1 \
+  --kitten-model=./kitten-nano-en-v0_1-fp16/model.fp16.onnx \
+  --kitten-voices=./kitten-nano-en-v0_1-fp16/voices.bin \
+  --kitten-tokens=./kitten-nano-en-v0_1-fp16/tokens.txt \
+  --kitten-data-dir=./kitten-nano-en-v0_1-fp16/espeak-ng-data \
+  --num-threads=2 \
+  --sid=0 \
+  --output-filename="./kitten-0.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
 
@@ -285,6 +302,36 @@ def add_kokoro_args(parser):
     )
 
 
+def add_kitten_args(parser):
+    parser.add_argument(
+        "--kitten-model",
+        type=str,
+        default="",
+        help="Path to model.onnx for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-voices",
+        type=str,
+        default="",
+        help="Path to voices.bin for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-tokens",
+        type=str,
+        default="",
+        help="Path to tokens.txt for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-data-dir",
+        type=str,
+        default="",
+        help="Path to the dict directory of espeak-ng.",
+    )
+
+
 def get_args():
     parser = argparse.ArgumentParser(
         formatter_class=argparse.ArgumentDefaultsHelpFormatter
@@ -293,6 +340,7 @@ def get_args():
     add_vits_args(parser)
     add_matcha_args(parser)
     add_kokoro_args(parser)
+    add_kitten_args(parser)
 
     parser.add_argument(
         "--tts-rule-fsts",
@@ -499,6 +547,12 @@ def main():
                 dict_dir=args.kokoro_dict_dir,
                 lexicon=args.kokoro_lexicon,
             ),
+            kitten=sherpa_onnx.OfflineTtsKittenModelConfig(
+                model=args.kitten_model,
+                voices=args.kitten_voices,
+                tokens=args.kitten_tokens,
+                data_dir=args.kitten_data_dir,
+            ),
             provider=args.provider,
             debug=args.debug,
             num_threads=args.num_threads,

@@ -12,7 +12,7 @@ generated audio.
 
 Usage:
 
-Example (1/7)
+Example (1/8)
 
 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 (2/7)
+Example (2/8)
 
 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 (3/7)
+Example (3/8)
 
 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 (4/7)
+Example (4/8)
 
 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 (5/7)
+Example (5/8)
 
 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
@@ -89,7 +89,7 @@ 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 (6/7)
+Example (6/8)
 
 (This version of kokoro supports only English)
 
@@ -106,9 +106,9 @@ python3 ./python-api-examples/offline-tts.py \
   --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."
+  "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 (7/7)
+Example (7/8)
 
 (This version of kokoro supports English, Chinese, etc.)
 
@@ -129,6 +129,23 @@ python3 ./python-api-examples/offline-tts.py \
   --output-filename="./kokoro-18-zh-en.wav" \
   "中英文语音合成测试。This is generated by next generation Kaldi using Kokoro without Misaki. 你觉得中英文说的如何呢？"
 
+Example (8/8)
+
+curl -SL -O https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/kitten-nano-en-v0_1-fp16.tar.bz2
+tar xf kitten-nano-en-v0_1-fp16.tar.bz2
+rm kitten-nano-en-v0_1-fp16.tar.bz2
+
+python3 ./python-api-examples/offline-tts.py \
+  --debug=1 \
+  --kitten-model=./kitten-nano-en-v0_1-fp16/model.fp16.onnx \
+  --kitten-voices=./kitten-nano-en-v0_1-fp16/voices.bin \
+  --kitten-tokens=./kitten-nano-en-v0_1-fp16/tokens.txt \
+  --kitten-data-dir=./kitten-nano-en-v0_1-fp16/espeak-ng-data \
+  --num-threads=2 \
+  --sid=0 \
+  --output-filename="./kitten-0.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
 
@@ -272,6 +289,36 @@ def add_kokoro_args(parser):
     )
 
 
+def add_kitten_args(parser):
+    parser.add_argument(
+        "--kitten-model",
+        type=str,
+        default="",
+        help="Path to model.onnx for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-voices",
+        type=str,
+        default="",
+        help="Path to voices.bin for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-tokens",
+        type=str,
+        default="",
+        help="Path to tokens.txt for kitten",
+    )
+
+    parser.add_argument(
+        "--kitten-data-dir",
+        type=str,
+        default="",
+        help="Path to the dict directory of espeak-ng.",
+    )
+
+
 def get_args():
     parser = argparse.ArgumentParser(
         formatter_class=argparse.ArgumentDefaultsHelpFormatter
@@ -280,6 +327,7 @@ def get_args():
     add_vits_args(parser)
     add_matcha_args(parser)
     add_kokoro_args(parser)
+    add_kitten_args(parser)
 
     parser.add_argument(
         "--tts-rule-fsts",
@@ -382,6 +430,12 @@ def main():
                 dict_dir=args.kokoro_dict_dir,
                 lexicon=args.kokoro_lexicon,
             ),
+            kitten=sherpa_onnx.OfflineTtsKittenModelConfig(
+                model=args.kitten_model,
+                voices=args.kitten_voices,
+                tokens=args.kitten_tokens,
+                data_dir=args.kitten_data_dir,
+            ),
             provider=args.provider,
             debug=args.debug,
             num_threads=args.num_threads,

@@ -44,6 +44,7 @@ from _sherpa_onnx import (
     OfflineTransducerModelConfig,
     OfflineTts,
     OfflineTtsConfig,
+    OfflineTtsKittenModelConfig,
     OfflineTtsKokoroModelConfig,
     OfflineTtsMatchaModelConfig,
     OfflineTtsModelConfig,