rhasspy/piper-voices duplicate as of 2024-07-05

README.md

@@ -1,3 +1,7 @@
----
-license: mit
----
+---
+license: mit
+---
+
+**Fork from:** [rhasspy/piper-voices](https://huggingface.co/rhasspy/piper-voices).
+
+For checkpoints that you can use to [train your own voices](https://github.com/rhasspy/piper/blob/master/TRAINING.md), see [piper-checkpoints](https://huggingface.co/datasets/rhasspy/piper-checkpoints/tree/main)

_script/voice_names.sh

@@ -0,0 +1,7 @@
+#!/usr/bin/env bash
+set -eo pipefail
+
+this_dir="$( cd "$( dirname "$0" )" && pwd )"
+repo_dir="$(realpath "${this_dir}/../")"
+
+find "${repo_dir}" -type f -name '*.onnx' -exec basename '{}' '.onnx' \; | sort | uniq

_script/voicefest.py

@@ -0,0 +1,325 @@
+#!/usr/bin/env python3
+import hashlib
+import json
+import unittest
+from dataclasses import dataclass
+from pathlib import Path
+from typing import Set
+
+_DIR = Path(__file__).parent
+_REPO_DIR = _DIR.parent
+
+
+@dataclass
+class Language:
+    native: str
+    english: str
+    country: str
+
+
+_LANGUAGES = {
+    "ar_JO": Language("العربية", "Arabic", "Jordan"),
+    "ca_ES": Language("Català", "Catalan", "Spain"),
+    "cs_CZ": Language("Čeština", "Czech", "Czech Republic"),
+    "cy_GB": Language("Cymraeg", "Welsh", "Great Britain"),
+    "da_DK": Language("Dansk", "Danish", "Denmark"),
+    "de_DE": Language("Deutsch", "German", "Germany"),
+    "el_GR": Language("Ελληνικά", "Greek", "Greece"),
+    "en_GB": Language("English", "English", "Great Britain"),
+    "en_US": Language("English", "English", "United States"),
+    "es_ES": Language("Español", "Spanish", "Spain"),
+    "es_MX": Language("Español", "Spanish", "Mexico"),
+    "fa_IR": Language("فارسی", "Farsi", "Iran"),
+    "fi_FI": Language("Suomi", "Finnish", "Finland"),
+    "fr_FR": Language("Français", "French", "France"),
+    "is_IS": Language("íslenska", "Icelandic", "Iceland"),
+    "it_IT": Language("Italiano", "Italian", "Italy"),
+    "hu_HU": Language("Magyar", "Hungarian", "Hungary"),
+    "ka_GE": Language("ქართული ენა", "Georgian", "Georgia"),
+    "kk_KZ": Language("қазақша", "Kazakh", "Kazakhstan"),
+    "lb_LU": Language("Lëtzebuergesch", "Luxembourgish", "Luxembourg"),
+    "ne_NP": Language("नेपाली", "Nepali", "Nepal"),
+    "nl_BE": Language("Nederlands", "Dutch", "Belgium"),
+    "nl_NL": Language("Nederlands", "Dutch", "Netherlands"),
+    "no_NO": Language("Norsk", "Norwegian", "Norway"),
+    "pl_PL": Language("Polski", "Polish", "Poland"),
+    "pt_BR": Language("Português", "Portuguese", "Brazil"),
+    "pt_PT": Language("Português", "Portuguese", "Portugal"),
+    "ro_RO": Language("Română", "Romanian", "Romania"),
+    "ru_RU": Language("Русский", "Russian", "Russia"),
+    "sk_SK": Language("Slovenčina", "Slovak", "Slovakia"),
+    "sl_SI": Language("Slovenščina", "Slovenian", "Slovenia"),
+    "sr_RS": Language("srpski", "Serbian", "Serbia"),
+    "sv_SE": Language("Svenska", "Swedish", "Sweden"),
+    "sw_CD": Language("Kiswahili", "Swahili", "Democratic Republic of the Congo"),
+    "tr_TR": Language("Türkçe", "Turkish", "Turkey"),
+    "uk_UA": Language("украї́нська мо́ва", "Ukrainian", "Ukraine"),
+    "vi_VN": Language("Tiếng Việt", "Vietnamese", "Vietnam"),
+    "zh_CN": Language("简体中文", "Chinese", "China"),
+}
+
+# -----------------------------------------------------------------------------
+
+
+def add_languages():
+    for onnx_path in _REPO_DIR.rglob("*.onnx"):
+        config_path = f"{onnx_path}.json"
+        with open(config_path, "r", encoding="utf-8") as config_file:
+            config = json.load(config_file)
+
+        lang_code, dataset, quality = onnx_path.stem.split("-")
+        is_changed = False
+
+        lang_info = _LANGUAGES.get(lang_code)
+        assert lang_info is not None, f"Missing name for language: {lang_code}"
+
+        lang_family, lang_region = lang_code.split("_", maxsplit=1)
+        lang_dict = {
+            "code": lang_code,
+            "family": lang_family,
+            "region": lang_region,
+            "name_native": lang_info.native,
+            "name_english": lang_info.english,
+            "country_english": lang_info.country,
+        }
+
+        if "language" not in config:
+            config["language"] = lang_dict
+            is_changed = True
+        else:
+            current_lang_dict = config["language"]
+            if "code" not in current_lang_dict:
+                current_lang_dict["code"] = lang_dict["code"]
+                is_changed = True
+
+            if "family" not in current_lang_dict:
+                current_lang_dict["family"] = lang_dict["family"]
+                is_changed = True
+
+            if "region" not in current_lang_dict:
+                current_lang_dict["region"] = lang_dict["region"]
+                is_changed = True
+
+            if "name_native" not in current_lang_dict:
+                current_lang_dict["name_native"] = lang_dict["name_native"]
+                is_changed = True
+
+            if "name_english" not in current_lang_dict:
+                current_lang_dict["name_english"] = lang_dict["name_english"]
+                is_changed = True
+
+            if "country_english" not in current_lang_dict:
+                current_lang_dict["country_english"] = lang_dict["country_english"]
+                is_changed = True
+
+        if "dataset" not in config:
+            config["dataset"] = dataset
+            is_changed = True
+
+        if "quality" not in config["audio"]:
+            config["audio"]["quality"] = quality
+            is_changed = True
+
+        if is_changed:
+            with open(config_path, "w", encoding="utf-8") as config_file:
+                json.dump(config, config_file, ensure_ascii=False, indent=2)
+
+
+# -----------------------------------------------------------------------------
+
+
+class VoiceTest(unittest.TestCase):
+    def test_voices(self):
+        used_aliases: Set[str] = set()
+
+        for onnx_path in _REPO_DIR.rglob("*.onnx"):
+            with self.subTest(onnx_path=onnx_path):
+                self.assertGreater(onnx_path.stat().st_size, 0, "Empty onnx file")
+
+                # Load JSON config for voice
+                config_path = onnx_path.parent / f"{onnx_path.name}.json"
+                with open(config_path, "r", encoding="utf-8") as config_file:
+                    config = json.load(config_file)
+
+                # Verify config
+                self.assertIn(
+                    "piper_version", config, "Missing piper_version in config"
+                )
+                self.assertIn("language", config, "Missing language in config")
+                self.assertIn("dataset", config, "Missing dataset in config")
+                self.assertIn(
+                    "quality", config["audio"], "Missing audio quality in config"
+                )
+
+                # Verify directory structure
+                # <lang_family>/<lang_code>/<dataset>/<quality>/
+                quality_dir = onnx_path.parent
+                dataset_dir = quality_dir.parent
+                lang_code_dir = dataset_dir.parent
+                lang_family_dir = lang_code_dir.parent
+
+                self.assertEqual(
+                    lang_family_dir.name,
+                    config["language"]["family"],
+                    "Wrong lang family dir",
+                )
+                self.assertEqual(
+                    lang_code_dir.name,
+                    config["language"]["code"],
+                    "Wrong lang code dir",
+                )
+                self.assertEqual(
+                    dataset_dir.name, config["dataset"], "Wrong dataset dir"
+                )
+                self.assertEqual(
+                    quality_dir.name, config["audio"]["quality"], "Wrong quality dir"
+                )
+                self.assertIn(lang_code_dir.name, _LANGUAGES, "Unknown language code")
+
+                # Verify file names
+                file_lang_code, file_dataset, file_quality = onnx_path.stem.split("-")
+                file_lang_family = file_lang_code.split("_", maxsplit=1)[0]
+
+                self.assertEqual(
+                    file_lang_family,
+                    config["language"]["family"],
+                    "Wrong lang family file",
+                )
+                self.assertEqual(
+                    file_lang_code, config["language"]["code"], "Wrong lang code file"
+                )
+                self.assertEqual(file_dataset, config["dataset"], "Wrong dataset file")
+                self.assertEqual(
+                    file_quality, config["audio"]["quality"], "Wrong quality"
+                )
+
+                # Verify aliases are unique
+                aliases_path = onnx_path.parent / "ALIASES"
+                if aliases_path.exists():
+                    with open(aliases_path, "r", encoding="utf-8") as aliases_file:
+                        for alias in aliases_file:
+                            alias = alias.strip()
+                            self.assertNotIn(
+                                alias,
+                                used_aliases,
+                                "Alias is already in use by another voice",
+                            )
+                            used_aliases.add(alias)
+
+
+def run_tests() -> None:
+    runner = unittest.TextTestRunner()
+    result = runner.run(unittest.makeSuite(VoiceTest))
+    assert not result.failures, "Test failures"
+
+
+# -----------------------------------------------------------------------------
+
+
+def write_voices_json() -> None:
+    # {
+    #   "<family>_<region>-<dataset>-<quality>": {
+    #     "key": "<voice_key>",
+    #     "name": "<dataset>",
+    #     "language": {
+    #       "code": "<family>_<region>",
+    #       "family": "<family>",
+    #       "region": "<region>",
+    #       "name_native": "<native>",
+    #       "name_english": "<english>",
+    #       "country_english": "<country>",
+    #     },
+    #     "quality": "<quality>",  // x_low, low, medium, high
+    #     "num_speakers": int,
+    #     "speaker_id_map": {
+    #       "name": int,
+    #       ...
+    #     }
+    #     "files": {
+    #       "relative/path/to/file": {
+    #         "size_bytes": int,
+    #         "md5_digest": str,        // hex
+    #       },
+    #       ...
+    #     },
+    #     "aliases": ["alias", ...],
+    #   },
+    #   ...
+    # }
+    voices = {}
+
+    for onnx_path in sorted(_REPO_DIR.rglob("*.onnx")):
+        voice_dir = onnx_path.parent
+        config_path = voice_dir / f"{onnx_path.name}.json"
+        with open(config_path, "r", encoding="utf-8") as config_file:
+            config = json.load(config_file)
+
+        quality = config["audio"]["quality"]
+        dataset = config["dataset"]
+        lang_code = config["language"]["code"]
+        lang_family, lang_region = lang_code.split("_", maxsplit=1)
+        lang_names = _LANGUAGES[lang_code]
+        voice_key = f"{lang_code}-{dataset}-{quality}"
+
+        model_card_path = voice_dir / "MODEL_CARD"
+        assert model_card_path.exists(), f"Missing {model_card_path}"
+
+        aliases: Set[str] = set()
+        aliases_path = voice_dir / "ALIASES"
+        if aliases_path.exists():
+            with open(aliases_path, "r", encoding="utf-8") as aliases_file:
+                for alias in aliases_file:
+                    aliases.add(alias.strip())
+
+        voices[voice_key] = {
+            "key": voice_key,
+            "name": dataset,
+            "language": {
+                "code": lang_code,
+                "family": lang_family,
+                "region": lang_region,
+                "name_native": lang_names.native,
+                "name_english": lang_names.english,
+                "country_english": lang_names.country,
+            },
+            "quality": quality,
+            "num_speakers": config["num_speakers"],
+            "speaker_id_map": config.get("speaker_id_map", {}),
+            "files": {
+                str(file_path.relative_to(_REPO_DIR)): {
+                    "size_bytes": file_path.stat().st_size,
+                    "md5_digest": get_file_hash(file_path),
+                }
+                for file_path in (
+                    onnx_path,
+                    config_path,
+                    model_card_path,
+                )
+            },
+            "aliases": sorted(list(aliases)),
+        }
+
+    with open(_REPO_DIR / "voices.json", "w", encoding="utf-8") as voices_file:
+        json.dump(voices, voices_file, indent=4, ensure_ascii=False)
+
+
+def get_file_hash(path, bytes_per_chunk: int = 8192) -> str:
+    """Hash a file in chunks using md5."""
+    path_hash = hashlib.md5()
+    with open(path, "rb") as path_file:
+        chunk = path_file.read(bytes_per_chunk)
+        while chunk:
+            path_hash.update(chunk)
+            chunk = path_file.read(bytes_per_chunk)
+
+    return path_hash.hexdigest()
+
+
+# -----------------------------------------------------------------------------
+
+if __name__ == "__main__":
+    add_languages()
+    run_tests()
+
+    print("Writing voices.json")
+    write_voices_json()

ar/ar_JO/kareem/low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for kareem (low)
+
+* Language: ar_JO (Arabic, Jordan)
+* Speakers: 1
+* Quality: low
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://github.com/AliMokhammad/arabicttstrain/
+* License: See URL
+
+## Training
+
+Finetuned from U.S English lessac voice (low quality).

ar/ar_JO/kareem/low/ar_JO-kareem-low.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2887e9d68b125965c747e1371fa21e1cef19555ea98d0795a0d5d71188b13890
+size 63201294

ar/ar_JO/kareem/low/ar_JO-kareem-low.onnx.json

@@ -0,0 +1,508 @@
+{
+  "dataset": "kareem",
+  "audio": {
+    "sample_rate": 16000,
+    "quality": "low"
+  },
+  "espeak": {
+    "voice": "ar"
+  },
+  "language": {
+    "code": "ar_JO",
+    "family": "ar",
+    "region": "JO",
+    "name_native": "العربية",
+    "name_english": "Arabic",
+    "country_english": "Jordan"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "X": [
+      156
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      154
+    ],
+    "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
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̊": [
+      158
+    ],
+    "̝": [
+      157
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0"
+}

ar/ar_JO/kareem/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for kareem (medium)
+
+* Language: ar_JO (Arabic, Jordan)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/AliMokhammad/arabicttstrain/
+* License: See URL
+
+## Training
+
+Finetuned from U.S English lessac voice (medium quality).

ar/ar_JO/kareem/medium/ar_JO-kareem-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e95cab07b679da603bba17c4dec7ab3111320571964ee95c0379603c086491e
+size 63201294

ar/ar_JO/kareem/medium/ar_JO-kareem-medium.onnx.json

@@ -0,0 +1,508 @@
+{
+  "dataset": "kareem",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "ar"
+  },
+  "language": {
+    "code": "ar_JO",
+    "family": "ar",
+    "region": "JO",
+    "name_native": "العربية",
+    "name_english": "Arabic",
+    "country_english": "Jordan"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "X": [
+      156
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      154
+    ],
+    "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
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̊": [
+      158
+    ],
+    "̝": [
+      157
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0"
+}

ca/ca_ES/upc_ona/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for upc_ona (medium)
+
+* Language: ca_ES (Catalan, Spain)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora
+* License: CC BY-SA 3.0 ES
+
+## Training
+
+Finetuned from U.S English lessac voice (medium quality).

ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb652db8c11a4475527346cf3241cb064d1ba393cf370f3f2ec09a872d118fd
+size 63201294

ca/ca_ES/upc_ona/medium/ca_ES-upc_ona-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "ca"
+  },
+  "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": "ca_ES",
+    "family": "ca",
+    "region": "ES",
+    "name_native": "Català",
+    "name_english": "Catalan",
+    "country_english": "Spain"
+  },
+  "dataset": "upc_ona"
+}

ca/ca_ES/upc_ona/x_low/ALIASES

@@ -0,0 +1 @@
+ca-upc_ona-x-low

ca/ca_ES/upc_ona/x_low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for upc_ona (x_low)
+
+* Language: ca_ES (Catalan, Spain)
+* Speakers: 1
+* Quality: x_low
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora
+* License: CC BY-SA 3.0 ES
+
+## Training
+
+Trained from scratch.

ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13661d26423e0c791823823a5971f4e1aaf644a62e65e0e94d299c0e70560e14
+size 20628813

ca/ca_ES/upc_ona/x_low/ca_ES-upc_ona-x_low.onnx.json

@@ -0,0 +1,420 @@
+{
+  "audio": {
+    "sample_rate": 16000,
+    "quality": "x_low"
+  },
+  "espeak": {
+    "voice": "ca"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "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
+    ]
+  },
+  "num_symbols": 130,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "0.2.0",
+  "language": {
+    "code": "ca_ES",
+    "family": "ca",
+    "region": "ES",
+    "name_native": "Català",
+    "name_english": "Catalan",
+    "country_english": "Spain"
+  },
+  "dataset": "upc_ona"
+}

ca/ca_ES/upc_pau/x_low/ALIASES

@@ -0,0 +1 @@
+ca-upc_pau-x-low

ca/ca_ES/upc_pau/x_low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for upc_pau (x_low)
+
+* Language: ca_ES (Catalan, Spain)
+* Speakers: 1
+* Quality: x_low
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://collectivat.cat/asr#upc-festcat-tts-corpora
+* License: CC BY-SA 3.0 ES
+
+## Training
+
+Trained from scratch.

ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c936a1a78b0a795af3c2422a0f2edb26303c389ff961616902ba12e26b489071
+size 28130791

ca/ca_ES/upc_pau/x_low/ca_ES-upc_pau-x_low.onnx.json

@@ -0,0 +1,420 @@
+{
+  "audio": {
+    "sample_rate": 16000,
+    "quality": "x_low"
+  },
+  "espeak": {
+    "voice": "ca"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "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
+    ]
+  },
+  "num_symbols": 130,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "0.2.0",
+  "language": {
+    "code": "ca_ES",
+    "family": "ca",
+    "region": "ES",
+    "name_native": "Català",
+    "name_english": "Catalan",
+    "country_english": "Spain"
+  },
+  "dataset": "upc_pau"
+}

cs/cs_CZ/jirka/low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for jirka (low)
+
+* Language: cs_CZ (Czech, Czech Republic)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://github.com/NabuCasa/voice-datasets
+* License: CC0
+
+## Training
+
+Finetuned from U.S. English lessac voice (low quality).

cs/cs_CZ/jirka/low/cs_CZ-jirka-low.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e73fb306a165b41927d2c9d882f71e9f1c86ac5edf37c5441370a6e4e6ef7d
+size 63201294

cs/cs_CZ/jirka/low/cs_CZ-jirka-low.onnx.json

@@ -0,0 +1,508 @@
+{
+  "audio": {
+    "sample_rate": 16000,
+    "quality": "low"
+  },
+  "espeak": {
+    "voice": "cs"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "X": [
+      156
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      154
+    ],
+    "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
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̊": [
+      158
+    ],
+    "̝": [
+      157
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "cs_CZ",
+    "family": "cs",
+    "region": "CZ",
+    "name_native": "Čeština",
+    "name_english": "Czech",
+    "country_english": "Czech Republic"
+  },
+  "dataset": "jirka"
+}

cs/cs_CZ/jirka/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for jirka (medium)
+
+* Language: cs_CZ (Czech, Czech Republic)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/NabuCasa/voice-datasets
+* License: CC0
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd5c900acacc8e8cbecd64347abb8de39c00a9d3104bed06fee92e4f319efc8
+size 63201294

cs/cs_CZ/jirka/medium/cs_CZ-jirka-medium.onnx.json

@@ -0,0 +1,508 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "cs"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "X": [
+      156
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      154
+    ],
+    "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
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̊": [
+      158
+    ],
+    "̝": [
+      157
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "cs_CZ",
+    "family": "cs",
+    "region": "CZ",
+    "name_native": "Čeština",
+    "name_english": "Czech",
+    "country_english": "Czech Republic"
+  },
+  "dataset": "jirka"
+}

cy/cy_GB/gwryw_gogleddol/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for gwryw_gogleddol (medium)
+
+* Language: cy_GB (Welsh, Great Britain)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://git.techiaith.bangor.ac.uk/data-porth-technolegau-iaith/corpws-talentau-llais
+* License: See URL
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

cy/cy_GB/gwryw_gogleddol/medium/cy_GB-gwryw_gogleddol-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7d87df65e2c67ddee49829906ec51982fe123d418472731dab696f4dcefe8c6
+size 63511038

cy/cy_GB/gwryw_gogleddol/medium/cy_GB-gwryw_gogleddol-medium.onnx.json

@@ -0,0 +1,502 @@
+{
+  "dataset": "gwryw_gogleddol",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "cy"
+  },
+  "language": {
+    "code": "cy_GB",
+    "family": "cy",
+    "region": "GB",
+    "name_native": "Cymraeg",
+    "name_english": "Welsh",
+    "country_english": "Great Britain"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "phoneme_type": "espeak",
+  "phoneme_map": {},
+  "phoneme_id_map": {
+    " ": [
+      3
+    ],
+    "!": [
+      4
+    ],
+    "\"": [
+      150
+    ],
+    "#": [
+      149
+    ],
+    "$": [
+      2
+    ],
+    "'": [
+      5
+    ],
+    "(": [
+      6
+    ],
+    ")": [
+      7
+    ],
+    ",": [
+      8
+    ],
+    "-": [
+      9
+    ],
+    ".": [
+      10
+    ],
+    "0": [
+      130
+    ],
+    "1": [
+      131
+    ],
+    "2": [
+      132
+    ],
+    "3": [
+      133
+    ],
+    "4": [
+      134
+    ],
+    "5": [
+      135
+    ],
+    "6": [
+      136
+    ],
+    "7": [
+      137
+    ],
+    "8": [
+      138
+    ],
+    "9": [
+      139
+    ],
+    ":": [
+      11
+    ],
+    ";": [
+      12
+    ],
+    "?": [
+      13
+    ],
+    "X": [
+      156
+    ],
+    "^": [
+      1
+    ],
+    "_": [
+      0
+    ],
+    "a": [
+      14
+    ],
+    "b": [
+      15
+    ],
+    "c": [
+      16
+    ],
+    "d": [
+      17
+    ],
+    "e": [
+      18
+    ],
+    "f": [
+      19
+    ],
+    "g": [
+      154
+    ],
+    "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
+    ],
+    "ʦ": [
+      155
+    ],
+    "ʰ": [
+      145
+    ],
+    "ʲ": [
+      119
+    ],
+    "ˈ": [
+      120
+    ],
+    "ˌ": [
+      121
+    ],
+    "ː": [
+      122
+    ],
+    "ˑ": [
+      123
+    ],
+    "˞": [
+      124
+    ],
+    "ˤ": [
+      146
+    ],
+    "̃": [
+      141
+    ],
+    "̧": [
+      140
+    ],
+    "̩": [
+      144
+    ],
+    "̪": [
+      142
+    ],
+    "̯": [
+      143
+    ],
+    "̺": [
+      152
+    ],
+    "̻": [
+      153
+    ],
+    "β": [
+      125
+    ],
+    "ε": [
+      147
+    ],
+    "θ": [
+      126
+    ],
+    "χ": [
+      127
+    ],
+    "ᵻ": [
+      128
+    ],
+    "↑": [
+      151
+    ],
+    "↓": [
+      148
+    ],
+    "ⱱ": [
+      129
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0"
+}

da/da_DK/talesyntese/medium/ALIASES

@@ -0,0 +1 @@
+da-nst_talesyntese-medium

da/da_DK/talesyntese/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for talesyntese (medium)
+
+* Language: da_DK (Danish, Denmark)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-21/
+* License: CC0
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9271efd25f7b8494bbd28d48dd675c8c119daa284f3ee488008935f515f1241
+size 63201294

da/da_DK/talesyntese/medium/da_DK-talesyntese-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "da"
+  },
+  "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": "0.2.0",
+  "language": {
+    "code": "da_DK",
+    "family": "da",
+    "region": "DK",
+    "name_native": "Dansk",
+    "name_english": "Danish",
+    "country_english": "Denmark"
+  },
+  "dataset": "talesyntese"
+}

de/de_DE/eva_k/x_low/ALIASES

@@ -0,0 +1 @@
+de-eva_k-x-low

de/de_DE/eva_k/x_low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for eva_k (x_low)
+
+* Language: de (German)
+* Speakers: 1
+* Quality: x_low
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/
+* License: See URL
+
+## Training
+
+Trained from scratch.

de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e88cf290fbfb768bf111330d2e8a46e376b0d85e3423a28bfebbc863a260dad8
+size 20628813

de/de_DE/eva_k/x_low/de_DE-eva_k-x_low.onnx.json

@@ -0,0 +1,420 @@
+{
+  "audio": {
+    "sample_rate": 16000,
+    "quality": "x_low"
+  },
+  "espeak": {
+    "voice": "de"
+  },
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1,
+    "noise_w": 0.8
+  },
+  "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
+    ]
+  },
+  "num_symbols": 130,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "0.2.0",
+  "language": {
+    "code": "de_DE",
+    "family": "de",
+    "region": "DE",
+    "name_native": "Deutsch",
+    "name_english": "German",
+    "country_english": "Germany"
+  },
+  "dataset": "eva_k"
+}

de/de_DE/karlsson/low/ALIASES

@@ -0,0 +1 @@
+de-karlsson-low

de/de_DE/karlsson/low/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for karlsson (low)
+
+* Language: de_DE (German, Germany)
+* Speakers: 1
+* Quality: low
+* Samplerate: 16,000Hz
+
+## Dataset
+
+* URL: https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/
+* License: See URL
+
+## Training
+
+Finetuned from U.S. English Ryan voice (low quality).