Add Piper TTS voice models and .gitignore

- Bundle 40+ en_GB, en_US, zh_CN ONNX voices for offline synthesis
- Ignore build artifacts and IDE files

.gitignore

@@ -0,0 +1,218 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+.DS_Store

app.py

@@ -8,12 +8,14 @@ from chatterbox.mtl_tts import ChatterboxMultilingualTTS
 from kittentts import KittenTTS
 from piper import PiperVoice
 import soundfile as sf
+import wave
+import os
 
 # Model descriptions for better understanding
 MODEL_DESCRIPTIONS = {
     "ResembleAI/chatterbox": "Industrial-grade TTS solution with multilingual support",
     "KittenML/KittenTTS": "High-quality TTS with voice cloning capabilities using reference audio",
-    "piper-tts": "Lightweight, on-device TTS with multiple voice options",
+    "piper-tts": "Local on-device TTS with dynamic English and Chinese voice selection from Piper models",
 }
 
 # Models dictionary
@@ -45,12 +47,41 @@ except RuntimeError as e:
 # Initialize KittenTTS model
 kittentts_model = KittenTTS("KittenML/kitten-tts-nano-0.2")
 
-# Initialize Piper model
-try:
-    piper_voice = PiperVoice.load("en_US-lessac-medium")
-except Exception as e:
-    print(f"Error loading Piper voice: {e}")
-    piper_voice = None
+# Scan Piper voices
+def scan_piper_voices():
+    voices_dir = "src/voices/piper_voices"
+    voices_by_lang = {'English': {}, 'Chinese': {}}
+    
+    # Chinese: only huayan medium
+    chinese_path = os.path.join(voices_dir, "zh", "zh_CN", "huayan", "medium", "zh_CN-huayan-medium.onnx")
+    if os.path.exists(chinese_path):
+        voices_by_lang['Chinese']['huayan (zh_CN)'] = chinese_path
+    
+    # English voices
+    en_dir = os.path.join(voices_dir, "en")
+    for root, dirs, files in os.walk(en_dir):
+        if len(root.split(os.sep)) < 5:  # Skip if not deep enough
+            continue
+        parts = root.split(os.sep)
+        if len(parts) >= 5 and parts[-1] in ['medium', 'high']:
+            locale = parts[-3]  # en_GB or en_US
+            voice_name = parts[-2]  # alan, etc.
+            quality = parts[-1]  # medium or high
+            
+            for file in files:
+                if file.endswith('.onnx') and f"{locale}-{voice_name}-{quality}" in file:
+                    path = os.path.join(root, file)
+                    label = f"{voice_name} ({locale})"
+                    # Prefer medium over high
+                    if quality == 'medium' or label not in voices_by_lang['English']:
+                        voices_by_lang['English'][label] = path
+                    break  # Assume one .onnx per dir
+    
+    return voices_by_lang
+
+voices_by_lang = scan_piper_voices()
+
+# No global piper_voice, load dynamically
 
 def generate_speech(text, language, audio_prompt=None):
     """
@@ -109,36 +140,39 @@ def generate_kittentts_speech(text, audio_prompt=None):
         sf.write(tmp_file.name, wav, 24000)
         return tmp_file.name
 
-def generate_piper_speech(text):
+def generate_piper_speech(text, lang, voice):
     """
-    Generate speech from text using Piper TTS
+    Generate speech from text using Piper TTS with selected voice
     
     Args:
         text (str): Text to convert to speech
+        lang (str): Language ('English' or 'Chinese')
+        voice (str): Selected voice label
     
     Returns:
-        str: Path to the generated audio file
+        tuple: (audio_path, error_msg) - path if success, None and error if fail
     """
-    if piper_voice is None:
-        raise RuntimeError("Piper voice model not loaded")
+    if not text.strip():
+        return None, "Please enter text to synthesize."
     
-    # Generate speech using Piper
-    audio_data = piper_voice.synthesize(text)
+    if voice not in voices_by_lang.get(lang, {}):
+        return None, f"Invalid voice selection for {lang}."
     
-    # Save to a temporary file
-    with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_file:
-        sf.write(tmp_file.name, audio_data, piper_voice.sample_rate)
-        return tmp_file.name
+    onnx_path = voices_by_lang[lang][voice]
+    
+    try:
+        piper_voice = PiperVoice.load(onnx_path)
+        with tempfile.NamedTemporaryFile(suffix=".wav", delete=False) as tmp_file:
+            with wave.open(tmp_file.name, "wb") as wav_file:
+                piper_voice.synthesize_wav(text, wav_file)
+            return tmp_file.name, ""
+    except Exception as e:
+        return None, f"Error synthesizing speech: {str(e)}"
 
-# Helper functions
-def get_rating_emoji(rating: str) -> str:
-    """Convert rating to emoji."""
-    if rating == "Excellent":
-        return "🟢"
-    elif rating == "Good":
-        return "🟡"
-    else:
-        return "🟠"
+def update_piper_voices(lang):
+    choices = list(voices_by_lang.get(lang, {}).keys())
+    value = choices[0] if choices else None
+    return gr.update(choices=choices, value=value)
 
 def create_model_card(repo: str) -> str:
     """Create a formatted model card with ratings and description."""

src/voices/piper_voices/en/en_GB/alan/medium/en_GB-alan-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a309668932205e762801f1efc2736cd4b0120329622adf62be09e56339d3330
+size 63201294

src/voices/piper_voices/en/en_GB/alan/medium/en_GB-alan-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "en-gb-x-rp"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    "_": [
+      0
+    ],
+    "^": [
+      1
+    ],
+    "$": [
+      2
+    ],
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "h": [
+      20
+    ],
+    "i": [
+      21
+    ],
+    "j": [
+      22
+    ],
+    "k": [
+      23
+    ],
+    "l": [
+      24
+    ],
+    "m": [
+      25
+    ],
+    "n": [
+      26
+    ],
+    "o": [
+      27
+    ],
+    "p": [
+      28
+    ],
+    "q": [
+      29
+    ],
+    "r": [
+      30
+    ],
+    "s": [
+      31
+    ],
+    "t": [
+      32
+    ],
+    "u": [
+      33
+    ],
+    "v": [
+      34
+    ],
+    "w": [
+      35
+    ],
+    "x": [
+      36
+    ],
+    "y": [
+      37
+    ],
+    "z": [
+      38
+    ],
+    "æ": [
+      39
+    ],
+    "ç": [
+      40
+    ],
+    "ð": [
+      41
+    ],
+    "ø": [
+      42
+    ],
+    "ħ": [
+      43
+    ],
+    "ŋ": [
+      44
+    ],
+    "œ": [
+      45
+    ],
+    "ǀ": [
+      46
+    ],
+    "ǁ": [
+      47
+    ],
+    "ǂ": [
+      48
+    ],
+    "ǃ": [
+      49
+    ],
+    "ɐ": [
+      50
+    ],
+    "ɑ": [
+      51
+    ],
+    "ɒ": [
+      52
+    ],
+    "ɓ": [
+      53
+    ],
+    "ɔ": [
+      54
+    ],
+    "ɕ": [
+      55
+    ],
+    "ɖ": [
+      56
+    ],
+    "ɗ": [
+      57
+    ],
+    "ɘ": [
+      58
+    ],
+    "ə": [
+      59
+    ],
+    "ɚ": [
+      60
+    ],
+    "ɛ": [
+      61
+    ],
+    "ɜ": [
+      62
+    ],
+    "ɞ": [
+      63
+    ],
+    "ɟ": [
+      64
+    ],
+    "ɠ": [
+      65
+    ],
+    "ɡ": [
+      66
+    ],
+    "ɢ": [
+      67
+    ],
+    "ɣ": [
+      68
+    ],
+    "ɤ": [
+      69
+    ],
+    "ɥ": [
+      70
+    ],
+    "ɦ": [
+      71
+    ],
+    "ɧ": [
+      72
+    ],
+    "ɨ": [
+      73
+    ],
+    "ɪ": [
+      74
+    ],
+    "ɫ": [
+      75
+    ],
+    "ɬ": [
+      76
+    ],
+    "ɭ": [
+      77
+    ],
+    "ɮ": [
+      78
+    ],
+    "ɯ": [
+      79
+    ],
+    "ɰ": [
+      80
+    ],
+    "ɱ": [
+      81
+    ],
+    "ɲ": [
+      82
+    ],
+    "ɳ": [
+      83
+    ],
+    "ɴ": [
+      84
+    ],
+    "ɵ": [
+      85
+    ],
+    "ɶ": [
+      86
+    ],
+    "ɸ": [
+      87
+    ],
+    "ɹ": [
+      88
+    ],
+    "ɺ": [
+      89
+    ],
+    "ɻ": [
+      90
+    ],
+    "ɽ": [
+      91
+    ],
+    "ɾ": [
+      92
+    ],
+    "ʀ": [
+      93
+    ],
+    "ʁ": [
+      94
+    ],
+    "ʂ": [
+      95
+    ],
+    "ʃ": [
+      96
+    ],
+    "ʄ": [
+      97
+    ],
+    "ʈ": [
+      98
+    ],
+    "ʉ": [
+      99
+    ],
+    "ʊ": [
+      100
+    ],
+    "ʋ": [
+      101
+    ],
+    "ʌ": [
+      102
+    ],
+    "ʍ": [
+      103
+    ],
+    "ʎ": [
+      104
+    ],
+    "ʏ": [
+      105
+    ],
+    "ʐ": [
+      106
+    ],
+    "ʑ": [
+      107
+    ],
+    "ʒ": [
+      108
+    ],
+    "ʔ": [
+      109
+    ],
+    "ʕ": [
+      110
+    ],
+    "ʘ": [
+      111
+    ],
+    "ʙ": [
+      112
+    ],
+    "ʛ": [
+      113
+    ],
+    "ʜ": [
+      114
+    ],
+    "ʝ": [
+      115
+    ],
+    "ʟ": [
+      116
+    ],
+    "ʡ": [
+      117
+    ],
+    "ʢ": [
+      118
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "β": [
+      125
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "ⱱ": [
+      129
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    "̧": [
+      140
+    ],
+    "̃": [
+      141
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̩": [
+      144
+    ],
+    "ʰ": [
+      145
+    ],
+    "ˤ": [
+      146
+    ],
+    "ε": [
+      147
+    ],
+    "↓": [
+      148
+    ],
+    "#": [
+      149
+    ],
+    "\"": [
+      150
+    ],
+    "↑": [
+      151
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "en_GB",
+    "family": "en",
+    "region": "GB",
+    "name_native": "English",
+    "name_english": "English",
+    "country_english": "Great Britain"
+  },
+  "dataset": "alan"
+}

src/voices/piper_voices/en/en_US/amy/medium/en_US-amy-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3a6e47b57b8c7fbe6a0ce2518161a50f59a9cdd8a50835c02cb02bdd6206c18
+size 63201294

src/voices/piper_voices/en/en_US/amy/medium/en_US-amy-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "en-us"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    "_": [
+      0
+    ],
+    "^": [
+      1
+    ],
+    "$": [
+      2
+    ],
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "h": [
+      20
+    ],
+    "i": [
+      21
+    ],
+    "j": [
+      22
+    ],
+    "k": [
+      23
+    ],
+    "l": [
+      24
+    ],
+    "m": [
+      25
+    ],
+    "n": [
+      26
+    ],
+    "o": [
+      27
+    ],
+    "p": [
+      28
+    ],
+    "q": [
+      29
+    ],
+    "r": [
+      30
+    ],
+    "s": [
+      31
+    ],
+    "t": [
+      32
+    ],
+    "u": [
+      33
+    ],
+    "v": [
+      34
+    ],
+    "w": [
+      35
+    ],
+    "x": [
+      36
+    ],
+    "y": [
+      37
+    ],
+    "z": [
+      38
+    ],
+    "æ": [
+      39
+    ],
+    "ç": [
+      40
+    ],
+    "ð": [
+      41
+    ],
+    "ø": [
+      42
+    ],
+    "ħ": [
+      43
+    ],
+    "ŋ": [
+      44
+    ],
+    "œ": [
+      45
+    ],
+    "ǀ": [
+      46
+    ],
+    "ǁ": [
+      47
+    ],
+    "ǂ": [
+      48
+    ],
+    "ǃ": [
+      49
+    ],
+    "ɐ": [
+      50
+    ],
+    "ɑ": [
+      51
+    ],
+    "ɒ": [
+      52
+    ],
+    "ɓ": [
+      53
+    ],
+    "ɔ": [
+      54
+    ],
+    "ɕ": [
+      55
+    ],
+    "ɖ": [
+      56
+    ],
+    "ɗ": [
+      57
+    ],
+    "ɘ": [
+      58
+    ],
+    "ə": [
+      59
+    ],
+    "ɚ": [
+      60
+    ],
+    "ɛ": [
+      61
+    ],
+    "ɜ": [
+      62
+    ],
+    "ɞ": [
+      63
+    ],
+    "ɟ": [
+      64
+    ],
+    "ɠ": [
+      65
+    ],
+    "ɡ": [
+      66
+    ],
+    "ɢ": [
+      67
+    ],
+    "ɣ": [
+      68
+    ],
+    "ɤ": [
+      69
+    ],
+    "ɥ": [
+      70
+    ],
+    "ɦ": [
+      71
+    ],
+    "ɧ": [
+      72
+    ],
+    "ɨ": [
+      73
+    ],
+    "ɪ": [
+      74
+    ],
+    "ɫ": [
+      75
+    ],
+    "ɬ": [
+      76
+    ],
+    "ɭ": [
+      77
+    ],
+    "ɮ": [
+      78
+    ],
+    "ɯ": [
+      79
+    ],
+    "ɰ": [
+      80
+    ],
+    "ɱ": [
+      81
+    ],
+    "ɲ": [
+      82
+    ],
+    "ɳ": [
+      83
+    ],
+    "ɴ": [
+      84
+    ],
+    "ɵ": [
+      85
+    ],
+    "ɶ": [
+      86
+    ],
+    "ɸ": [
+      87
+    ],
+    "ɹ": [
+      88
+    ],
+    "ɺ": [
+      89
+    ],
+    "ɻ": [
+      90
+    ],
+    "ɽ": [
+      91
+    ],
+    "ɾ": [
+      92
+    ],
+    "ʀ": [
+      93
+    ],
+    "ʁ": [
+      94
+    ],
+    "ʂ": [
+      95
+    ],
+    "ʃ": [
+      96
+    ],
+    "ʄ": [
+      97
+    ],
+    "ʈ": [
+      98
+    ],
+    "ʉ": [
+      99
+    ],
+    "ʊ": [
+      100
+    ],
+    "ʋ": [
+      101
+    ],
+    "ʌ": [
+      102
+    ],
+    "ʍ": [
+      103
+    ],
+    "ʎ": [
+      104
+    ],
+    "ʏ": [
+      105
+    ],
+    "ʐ": [
+      106
+    ],
+    "ʑ": [
+      107
+    ],
+    "ʒ": [
+      108
+    ],
+    "ʔ": [
+      109
+    ],
+    "ʕ": [
+      110
+    ],
+    "ʘ": [
+      111
+    ],
+    "ʙ": [
+      112
+    ],
+    "ʛ": [
+      113
+    ],
+    "ʜ": [
+      114
+    ],
+    "ʝ": [
+      115
+    ],
+    "ʟ": [
+      116
+    ],
+    "ʡ": [
+      117
+    ],
+    "ʢ": [
+      118
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "β": [
+      125
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "ⱱ": [
+      129
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    "̧": [
+      140
+    ],
+    "̃": [
+      141
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̩": [
+      144
+    ],
+    "ʰ": [
+      145
+    ],
+    "ˤ": [
+      146
+    ],
+    "ε": [
+      147
+    ],
+    "↓": [
+      148
+    ],
+    "#": [
+      149
+    ],
+    "\"": [
+      150
+    ],
+    "↑": [
+      151
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "en_US",
+    "family": "en",
+    "region": "US",
+    "name_native": "English",
+    "name_english": "English",
+    "country_english": "United States"
+  },
+  "dataset": "amy"
+}

src/voices/piper_voices/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9929917bf8cabb26fd528ea44d3a6699c11e87317a14765312420be230be0f3d
+size 63201294

src/voices/piper_voices/zh/zh_CN/huayan/medium/zh_CN-huayan-medium.onnx.json

@@ -0,0 +1,487 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "cmn"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    "_": [
+      0
+    ],
+    "^": [
+      1
+    ],
+    "$": [
+      2
+    ],
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "h": [
+      20
+    ],
+    "i": [
+      21
+    ],
+    "j": [
+      22
+    ],
+    "k": [
+      23
+    ],
+    "l": [
+      24
+    ],
+    "m": [
+      25
+    ],
+    "n": [
+      26
+    ],
+    "o": [
+      27
+    ],
+    "p": [
+      28
+    ],
+    "q": [
+      29
+    ],
+    "r": [
+      30
+    ],
+    "s": [
+      31
+    ],
+    "t": [
+      32
+    ],
+    "u": [
+      33
+    ],
+    "v": [
+      34
+    ],
+    "w": [
+      35
+    ],
+    "x": [
+      36
+    ],
+    "y": [
+      37
+    ],
+    "z": [
+      38
+    ],
+    "æ": [
+      39
+    ],
+    "ç": [
+      40
+    ],
+    "ð": [
+      41
+    ],
+    "ø": [
+      42
+    ],
+    "ħ": [
+      43
+    ],
+    "ŋ": [
+      44
+    ],
+    "œ": [
+      45
+    ],
+    "ǀ": [
+      46
+    ],
+    "ǁ": [
+      47
+    ],
+    "ǂ": [
+      48
+    ],
+    "ǃ": [
+      49
+    ],
+    "ɐ": [
+      50
+    ],
+    "ɑ": [
+      51
+    ],
+    "ɒ": [
+      52
+    ],
+    "ɓ": [
+      53
+    ],
+    "ɔ": [
+      54
+    ],
+    "ɕ": [
+      55
+    ],
+    "ɖ": [
+      56
+    ],
+    "ɗ": [
+      57
+    ],
+    "ɘ": [
+      58
+    ],
+    "ə": [
+      59
+    ],
+    "ɚ": [
+      60
+    ],
+    "ɛ": [
+      61
+    ],
+    "ɜ": [
+      62
+    ],
+    "ɞ": [
+      63
+    ],
+    "ɟ": [
+      64
+    ],
+    "ɠ": [
+      65
+    ],
+    "ɡ": [
+      66
+    ],
+    "ɢ": [
+      67
+    ],
+    "ɣ": [
+      68
+    ],
+    "ɤ": [
+      69
+    ],
+    "ɥ": [
+      70
+    ],
+    "ɦ": [
+      71
+    ],
+    "ɧ": [
+      72
+    ],
+    "ɨ": [
+      73
+    ],
+    "ɪ": [
+      74
+    ],
+    "ɫ": [
+      75
+    ],
+    "ɬ": [
+      76
+    ],
+    "ɭ": [
+      77
+    ],
+    "ɮ": [
+      78
+    ],
+    "ɯ": [
+      79
+    ],
+    "ɰ": [
+      80
+    ],
+    "ɱ": [
+      81
+    ],
+    "ɲ": [
+      82
+    ],
+    "ɳ": [
+      83
+    ],
+    "ɴ": [
+      84
+    ],
+    "ɵ": [
+      85
+    ],
+    "ɶ": [
+      86
+    ],
+    "ɸ": [
+      87
+    ],
+    "ɹ": [
+      88
+    ],
+    "ɺ": [
+      89
+    ],
+    "ɻ": [
+      90
+    ],
+    "ɽ": [
+      91
+    ],
+    "ɾ": [
+      92
+    ],
+    "ʀ": [
+      93
+    ],
+    "ʁ": [
+      94
+    ],
+    "ʂ": [
+      95
+    ],
+    "ʃ": [
+      96
+    ],
+    "ʄ": [
+      97
+    ],
+    "ʈ": [
+      98
+    ],
+    "ʉ": [
+      99
+    ],
+    "ʊ": [
+      100
+    ],
+    "ʋ": [
+      101
+    ],
+    "ʌ": [
+      102
+    ],
+    "ʍ": [
+      103
+    ],
+    "ʎ": [
+      104
+    ],
+    "ʏ": [
+      105
+    ],
+    "ʐ": [
+      106
+    ],
+    "ʑ": [
+      107
+    ],
+    "ʒ": [
+      108
+    ],
+    "ʔ": [
+      109
+    ],
+    "ʕ": [
+      110
+    ],
+    "ʘ": [
+      111
+    ],
+    "ʙ": [
+      112
+    ],
+    "ʛ": [
+      113
+    ],
+    "ʜ": [
+      114
+    ],
+    "ʝ": [
+      115
+    ],
+    "ʟ": [
+      116
+    ],
+    "ʡ": [
+      117
+    ],
+    "ʢ": [
+      118
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "β": [
+      125
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "ⱱ": [
+      129
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    "̧": [
+      140
+    ],
+    "̃": [
+      141
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̩": [
+      144
+    ],
+    "ʰ": [
+      145
+    ],
+    "ˤ": [
+      146
+    ],
+    "ε": [
+      147
+    ],
+    "↓": [
+      148
+    ],
+    "#": [
+      149
+    ],
+    "\"": [
+      150
+    ],
+    "↑": [
+      151
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "zh_CN",
+    "family": "zh",
+    "region": "CN",
+    "name_native": "简体中文",
+    "name_english": "Chinese",
+    "country_english": "China"
+  },
+  "dataset": "huayan"
+}