thorsten_emotional, marylux, dfki, serbski_institut, mihai voices

_script/voicefest.py

@@ -32,20 +32,66 @@ _LANGUAGES = {
     "it_IT": Language("Italiano", "Italian", "Italy"),
     "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"),
+    "ro_RO": Language("Română", "Romanian", "Romania"),
     "ru_RU": Language("Русский", "Russian", "Russia"),
+    "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
+
+        if "language" not in config:
+            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)
+            config["language"] = {
+                "code": lang_code,
+                "family": lang_family,
+                "region": lang_region,
+                "name_native": lang_info.native,
+                "name_english": lang_info.english,
+                "country_english": lang_info.country,
+            }
+            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):
@@ -109,7 +155,7 @@ class VoiceTest(unittest.TestCase):
                 )
                 self.assertEqual(file_dataset, config["dataset"], "Wrong dataset file")
                 self.assertEqual(
-                    file_quality, config["audio"]["quality"], "Wrong quality file"
+                    file_quality, config["audio"]["quality"], "Wrong quality"
                 )
 
                 # Verify aliases are unique
@@ -128,7 +174,8 @@ class VoiceTest(unittest.TestCase):
 
 def run_tests() -> None:
     runner = unittest.TextTestRunner()
-    runner.run(unittest.makeSuite(VoiceTest))
+    result = runner.run(unittest.makeSuite(VoiceTest))
+    assert not result.failures, "Test failures"
 
 
 # -----------------------------------------------------------------------------
@@ -236,6 +283,7 @@ def get_file_hash(path, bytes_per_chunk: int = 8192) -> str:
 # -----------------------------------------------------------------------------
 
 if __name__ == "__main__":
+    add_languages()
     run_tests()
 
     print("Writing voices.json")

de/de_DE/thorsten_emotional/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for thorsten_emotional (medium)
+
+* Language: de_DE (German, Germany)
+* Speakers: 8 (emotions)
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/thorstenMueller/Thorsten-Voice
+* License: CC0
+
+## Training
+
+Finetuned from German thorsten voice (medium quality).

de/de_DE/thorsten_emotional/medium/de_DE-thorsten_emotional-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1764e652266cd6dcebf1b95c61973df5970a5f5272e94b655ff1ddf9a99d1ff
+size 76745905

de/de_DE/thorsten_emotional/medium/de_DE-thorsten_emotional-medium.onnx.json

@@ -0,0 +1,502 @@
+{
+  "piper_version": "1.1.0",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "de"
+  },
+  "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": 8,
+  "speaker_id_map": {
+    "amused": 0,
+    "angry": 1,
+    "disgusted": 2,
+    "drunk": 3,
+    "neutral": 4,
+    "sleepy": 5,
+    "surprised": 6,
+    "whisper": 7
+  },
+  "language": {
+    "code": "de_DE",
+    "family": "de",
+    "region": "DE",
+    "name_native": "Deutsch",
+    "name_english": "German",
+    "country_english": "Germany"
+  },
+  "dataset": "thorsten_emotional"
+}

lb/lb_LU/marylux/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for marylux (medium)
+
+* Language: lb_LU (Luxembourgish, Luxembourg)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/marytts/marylux-data
+* License: http://creativecommons.org/licenses/by-nc-sa/4.0/
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

lb/lb_LU/marylux/medium/lb_LU-marylux-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4147ecacdd98932951d0f956555542de358d3ccff708d4996e305c3ce287097a
+size 63201294

lb/lb_LU/marylux/medium/lb_LU-marylux-medium.onnx.json

@@ -0,0 +1,502 @@
+{
+  "piper_version": "1.0.0",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "lb"
+  },
+  "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": {},
+  "language": {
+    "code": "lb_LU",
+    "family": "lb",
+    "region": "LU",
+    "name_native": "Lëtzebuergesch",
+    "name_english": "Luxembourgish",
+    "country_english": "Luxembourg"
+  },
+  "dataset": "marylux"
+}

ro/ro_RO/mihai/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for miahi (medium)
+
+* Language: ro_RO (Romanian, Romania)
+* 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).

ro/ro_RO/mihai/medium/ro_RO-mihai-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0608bbbd53c80267c09ece681b09f5199f54e792356684c8073738e5f15d29f
+size 63201294

ro/ro_RO/mihai/medium/ro_RO-mihai-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "piper_version": "1.0.0",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "ro"
+  },
+  "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": {},
+  "language": {
+    "code": "ro_RO",
+    "family": "ro",
+    "region": "RO",
+    "name_native": "Română",
+    "name_english": "Romanian",
+    "country_english": "Romania"
+  },
+  "dataset": "mihai"
+}

sr/sr_RS/serbski_institut/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for serbski_institut (medium)
+
+* Language: sr_RS (Serbian, Serbia)
+* Speakers: 2
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/marytts/serbski-institut-dsb-data
+* License: https://creativecommons.org/licenses/by-nc-sa/4.0/
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

sr/sr_RS/serbski_institut/medium/sr_RS-serbski_institut-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7003890cf596e653f660a4fd97fd17f57f1eceb6d9727abad9cd76d2fda0d80
+size 76733615

sr/sr_RS/serbski_institut/medium/sr_RS-serbski_institut-medium.onnx.json

@@ -0,0 +1,505 @@
+{
+  "piper_version": "1.0.0",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "sr"
+  },
+  "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": 2,
+  "speaker_id_map": {
+    "dsb": 0,
+    "hsb": 1
+  },
+  "language": {
+    "code": "sr_RS",
+    "family": "sr",
+    "region": "RS",
+    "name_native": "srpski",
+    "name_english": "Serbian",
+    "country_english": "Serbia"
+  },
+  "dataset": "serbski_institut"
+}

tr/tr_TR/dfki/medium/MODEL_CARD

@@ -0,0 +1,15 @@
+# Model card for dfki (medium)
+
+* Language: tr_TR (Turkish, Turkey)
+* Speakers: 1
+* Quality: medium
+* Samplerate: 22,050Hz
+
+## Dataset
+
+* URL: https://github.com/marytts/dfki-ot-data/
+* License: https://creativecommons.org/licenses/by-nc-sa/4.0/
+
+## Training
+
+Finetuned from U.S. English lessac voice (medium quality).

tr/tr_TR/dfki/medium/tr_TR-dfki-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2844717f524ab965d3fe86e60562cbb601d3e456836efcc2196cc3a14112a8fb
+size 63201294

tr/tr_TR/dfki/medium/tr_TR-dfki-medium.onnx.json

@@ -0,0 +1,493 @@
+{
+  "piper_version": "1.1.0",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "tr"
+  },
+  "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": {},
+  "language": {
+    "code": "tr_TR",
+    "family": "tr",
+    "region": "TR",
+    "name_native": "Türkçe",
+    "name_english": "Turkish",
+    "country_english": "Turkey"
+  },
+  "dataset": "dfki"
+}

voices.json

@@ -640,6 +640,36 @@
             "kk-iseke-x-low"
         ]
     },
+    "lb_LU-marylux-medium": {
+        "key": "lb_LU-marylux-medium",
+        "name": "marylux",
+        "language": {
+            "code": "lb_LU",
+            "family": "lb",
+            "region": "LU",
+            "name_native": "Lëtzebuergesch",
+            "name_english": "Luxembourgish",
+            "country_english": "Luxembourg"
+        },
+        "quality": "medium",
+        "num_speakers": 1,
+        "speaker_id_map": {},
+        "files": {
+            "lb/lb_LU/marylux/medium/lb_LU-marylux-medium.onnx": {
+                "size_bytes": 63201294,
+                "md5_digest": "966856e665a46cee45cb0cd2c475f8d5"
+            },
+            "lb/lb_LU/marylux/medium/lb_LU-marylux-medium.onnx.json": {
+                "size_bytes": 4979,
+                "md5_digest": "aea98b0e4fecaa0b3b7adc2048561095"
+            },
+            "lb/lb_LU/marylux/medium/MODEL_CARD": {
+                "size_bytes": 330,
+                "md5_digest": "1eeb3d600789cdd8b3f23866023d8543"
+            }
+        },
+        "aliases": []
+    },
     "pt_BR-faber-medium": {
         "key": "pt_BR-faber-medium",
         "name": "faber",
@@ -860,6 +890,45 @@
         },
         "aliases": []
     },
+    "de_DE-thorsten_emotional-medium": {
+        "key": "de_DE-thorsten_emotional-medium",
+        "name": "thorsten_emotional",
+        "language": {
+            "code": "de_DE",
+            "family": "de",
+            "region": "DE",
+            "name_native": "Deutsch",
+            "name_english": "German",
+            "country_english": "Germany"
+        },
+        "quality": "medium",
+        "num_speakers": 8,
+        "speaker_id_map": {
+            "amused": 0,
+            "angry": 1,
+            "disgusted": 2,
+            "drunk": 3,
+            "neutral": 4,
+            "sleepy": 5,
+            "surprised": 6,
+            "whisper": 7
+        },
+        "files": {
+            "de/de_DE/thorsten_emotional/medium/de_DE-thorsten_emotional-medium.onnx": {
+                "size_bytes": 76745905,
+                "md5_digest": "7cc67d24d9d0b34d7a4f6224d16236b9"
+            },
+            "de/de_DE/thorsten_emotional/medium/de_DE-thorsten_emotional-medium.onnx.json": {
+                "size_bytes": 5031,
+                "md5_digest": "1abac7e46522f774217c170da222f2a6"
+            },
+            "de/de_DE/thorsten_emotional/medium/MODEL_CARD": {
+                "size_bytes": 302,
+                "md5_digest": "91874c31e5b2e497ecda2ea8e6fda4a7"
+            }
+        },
+        "aliases": []
+    },
     "de_DE-ramona-low": {
         "key": "de_DE-ramona-low",
         "name": "ramona",
@@ -956,6 +1025,36 @@
             "da-nst_talesyntese-medium"
         ]
     },
+    "ro_RO-mihai-medium": {
+        "key": "ro_RO-mihai-medium",
+        "name": "mihai",
+        "language": {
+            "code": "ro_RO",
+            "family": "ro",
+            "region": "RO",
+            "name_native": "Română",
+            "name_english": "Romanian",
+            "country_english": "Romania"
+        },
+        "quality": "medium",
+        "num_speakers": 1,
+        "speaker_id_map": {},
+        "files": {
+            "ro/ro_RO/mihai/medium/ro_RO-mihai-medium.onnx": {
+                "size_bytes": 63201294,
+                "md5_digest": "45f4253916c93d3d05ad3fe1b07ea4f3"
+            },
+            "ro/ro_RO/mihai/medium/ro_RO-mihai-medium.onnx.json": {
+                "size_bytes": 4877,
+                "md5_digest": "f820f8ba65a8646c68792be581b85144"
+            },
+            "ro/ro_RO/mihai/medium/MODEL_CARD": {
+                "size_bytes": 277,
+                "md5_digest": "4075864685b207c9a98bf1af237a1502"
+            }
+        },
+        "aliases": []
+    },
     "is_IS-ugla-medium": {
         "key": "is_IS-ugla-medium",
         "name": "ugla",
@@ -3405,6 +3504,39 @@
         },
         "aliases": []
     },
+    "sr_RS-serbski_institut-medium": {
+        "key": "sr_RS-serbski_institut-medium",
+        "name": "serbski_institut",
+        "language": {
+            "code": "sr_RS",
+            "family": "sr",
+            "region": "RS",
+            "name_native": "srpski",
+            "name_english": "Serbian",
+            "country_english": "Serbia"
+        },
+        "quality": "medium",
+        "num_speakers": 2,
+        "speaker_id_map": {
+            "dsb": 0,
+            "hsb": 1
+        },
+        "files": {
+            "sr/sr_RS/serbski_institut/medium/sr_RS-serbski_institut-medium.onnx": {
+                "size_bytes": 76733615,
+                "md5_digest": "02c6e27ac7b4dfa84272df89edca9feb"
+            },
+            "sr/sr_RS/serbski_institut/medium/sr_RS-serbski_institut-medium.onnx.json": {
+                "size_bytes": 4999,
+                "md5_digest": "dacee7595352af9b4d78bb42237bd759"
+            },
+            "sr/sr_RS/serbski_institut/medium/MODEL_CARD": {
+                "size_bytes": 343,
+                "md5_digest": "407a5b8ebef4877405de2e89eb806633"
+            }
+        },
+        "aliases": []
+    },
     "sw_CD-lanfrica-medium": {
         "key": "sw_CD-lanfrica-medium",
         "name": "lanfrica",
@@ -3625,6 +3757,36 @@
         },
         "aliases": []
     },
+    "tr_TR-dfki-medium": {
+        "key": "tr_TR-dfki-medium",
+        "name": "dfki",
+        "language": {
+            "code": "tr_TR",
+            "family": "tr",
+            "region": "TR",
+            "name_native": "Türkçe",
+            "name_english": "Turkish",
+            "country_english": "Turkey"
+        },
+        "quality": "medium",
+        "num_speakers": 1,
+        "speaker_id_map": {},
+        "files": {
+            "tr/tr_TR/dfki/medium/tr_TR-dfki-medium.onnx": {
+                "size_bytes": 63201294,
+                "md5_digest": "f51287b350a042dd8d67b2b215145e5a"
+            },
+            "tr/tr_TR/dfki/medium/tr_TR-dfki-medium.onnx.json": {
+                "size_bytes": 4874,
+                "md5_digest": "d76424a40a79733bfbe59751e949b9ff"
+            },
+            "tr/tr_TR/dfki/medium/MODEL_CARD": {
+                "size_bytes": 319,
+                "md5_digest": "870d6bc19719328699449cb7b4dd56cf"
+            }
+        },
+        "aliases": []
+    },
     "ka_GE-natia-medium": {
         "key": "ka_GE-natia-medium",
         "name": "natia",