phoonnx-vits batch: piper + MMS, 1 model per subfolder

README.md

@@ -0,0 +1,14 @@
+---
+license: mit
+pipeline_tag: text-to-speech
+library_name: phoonnx
+tags: [phoonnx, vits, piper, mms, tts]
+---
+# phoonnx-vits
+Per-architecture mono-repo of **VITS** voices for [phoonnx](https://github.com/TigreGotico/phoonnx).
+One model per subfolder. Part of the [phoonnx community mirror](https://huggingface.co/collections/OpenVoiceOS/phoonnx-community-mirror-6a2204d302e0e7497870cd68).
+
+- `en_US-lessac-medium`, `en_GB-alba-medium`, `de_DE-thorsten-medium`, `fr_FR-siwis-medium` — Piper voices (espeak), mirror of `rhasspy/piper-voices` (mit).
+- `mms-eng`, `mms-spa`, `mms-fra`, `mms-deu` — Meta MMS-TTS (graphemes), ONNX from `willwade/mms-tts-multilingual-models-onnx`, tokenizer from `facebook/mms-tts-*` (cc-by-nc-4.0).
+
+Licenses follow the originals per subfolder.

de_DE-thorsten-medium/config.json

@@ -0,0 +1,487 @@
+{
+  "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
+    ]
+  },
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "speaker_id_map": {},
+  "piper_version": "1.0.0",
+  "language": {
+    "code": "de_DE",
+    "family": "de",
+    "region": "DE",
+    "name_native": "Deutsch",
+    "name_english": "German",
+    "country_english": "Germany"
+  },
+  "dataset": "thorsten"
+}

de_DE-thorsten-medium/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e64762d8e5118bb578f2eea6207e1a35a8e0c30595010b666f983fc87bb7819
+size 63201294

en_GB-alba-medium/config.json

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

en_GB-alba-medium/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:401369c4a81d09fdd86c32c5c864440811dbdcc66466cde2d64f7133a66ad03b
+size 63201294

en_US-lessac-medium/config.json

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

en_US-lessac-medium/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5efe09e69902187827af646e1a6e9d269dee769f9877d17b16b1b46eeaaf019f
+size 63201294

fr_FR-siwis-medium/config.json

@@ -0,0 +1,493 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "fr"
+  },
+  "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": "fr_FR",
+    "family": "fr",
+    "region": "FR",
+    "name_native": "Français",
+    "name_english": "French",
+    "country_english": "France"
+  },
+  "dataset": "siwis"
+}

fr_FR-siwis-medium/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641d1ab097da2b81128c076810edb052b385decc8be3381814802a64a73baf99
+size 63201294

mms-deu/config.json

@@ -0,0 +1,9 @@
+{
+ "phoneme_type": "graphemes",
+ "alphabet": "unicode",
+ "lang_code": "de",
+ "engine": "transformers",
+ "audio": {
+  "sample_rate": 16000
+ }
+}

mms-deu/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f0c099217fb53000ea4949316111c9ff755965b1b81d9c2566fe757774253af
+size 114022328

mms-deu/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "deu",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": " ",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

mms-deu/vocab.json

@@ -0,0 +1,47 @@
+{
+  " ": 0,
+  "-": 5,
+  "0": 44,
+  "1": 7,
+  "2": 2,
+  "3": 13,
+  "4": 11,
+  "5": 31,
+  "6": 30,
+  "7": 42,
+  "8": 8,
+  "_": 27,
+  "a": 9,
+  "b": 22,
+  "c": 33,
+  "d": 21,
+  "e": 38,
+  "f": 6,
+  "g": 4,
+  "h": 10,
+  "i": 34,
+  "j": 28,
+  "k": 37,
+  "l": 17,
+  "m": 15,
+  "n": 18,
+  "o": 25,
+  "p": 36,
+  "q": 3,
+  "r": 14,
+  "s": 29,
+  "t": 19,
+  "u": 26,
+  "v": 1,
+  "w": 40,
+  "x": 43,
+  "y": 23,
+  "z": 41,
+  "ß": 24,
+  "ä": 16,
+  "ë": 20,
+  "ï": 32,
+  "ö": 12,
+  "ü": 35,
+  "–": 39
+}

mms-eng/config.json

@@ -0,0 +1,9 @@
+{
+ "phoneme_type": "graphemes",
+ "alphabet": "unicode",
+ "lang_code": "en",
+ "engine": "transformers",
+ "audio": {
+  "sample_rate": 16000
+ }
+}

mms-eng/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58942e255596455b5230ce09cd0d685a808362f12ba0da0db79d5701971123a5
+size 114016952

mms-eng/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "eng",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "k",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

mms-eng/vocab.json

@@ -0,0 +1,40 @@
+{
+  " ": 19,
+  "'": 1,
+  "-": 14,
+  "0": 23,
+  "1": 15,
+  "2": 28,
+  "3": 11,
+  "4": 27,
+  "5": 35,
+  "6": 36,
+  "_": 30,
+  "a": 26,
+  "b": 24,
+  "c": 12,
+  "d": 5,
+  "e": 7,
+  "f": 20,
+  "g": 37,
+  "h": 6,
+  "i": 18,
+  "j": 16,
+  "k": 0,
+  "l": 21,
+  "m": 17,
+  "n": 29,
+  "o": 22,
+  "p": 13,
+  "q": 34,
+  "r": 25,
+  "s": 8,
+  "t": 33,
+  "u": 4,
+  "v": 32,
+  "w": 9,
+  "x": 31,
+  "y": 3,
+  "z": 2,
+  "–": 10
+}

mms-fra/config.json

@@ -0,0 +1,9 @@
+{
+ "phoneme_type": "graphemes",
+ "alphabet": "unicode",
+ "lang_code": "fr",
+ "engine": "transformers",
+ "audio": {
+  "sample_rate": 16000
+ }
+}

mms-fra/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c7ce08f95a3634dbd94293bc231de8af9970816904fb4401b9b7b652bc49cd
+size 114021560

mms-fra/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "fra",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "î",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

mms-fra/vocab.json

@@ -0,0 +1,46 @@
+{
+  " ": 29,
+  "'": 41,
+  "-": 2,
+  "_": 14,
+  "a": 19,
+  "b": 18,
+  "c": 10,
+  "d": 17,
+  "e": 15,
+  "f": 20,
+  "g": 11,
+  "h": 22,
+  "i": 16,
+  "j": 36,
+  "k": 25,
+  "l": 43,
+  "m": 42,
+  "n": 34,
+  "o": 35,
+  "p": 31,
+  "q": 9,
+  "r": 23,
+  "s": 26,
+  "t": 33,
+  "u": 4,
+  "v": 27,
+  "x": 8,
+  "y": 6,
+  "z": 1,
+  "à": 28,
+  "â": 38,
+  "ç": 39,
+  "è": 7,
+  "é": 24,
+  "ê": 13,
+  "ë": 32,
+  "î": 0,
+  "ï": 40,
+  "ô": 12,
+  "ù": 3,
+  "û": 5,
+  "ü": 37,
+  "œ": 21,
+  "–": 30
+}

mms-spa/config.json

@@ -0,0 +1,9 @@
+{
+ "phoneme_type": "graphemes",
+ "alphabet": "unicode",
+ "lang_code": "es",
+ "engine": "transformers",
+ "audio": {
+  "sample_rate": 16000
+ }
+}

mms-spa/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:721c3c85fb8967b29ce6c1b0a52e5626a6deacb12c6b015562f71ea64787e8d2
+size 114022328

mms-spa/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_blank": true,
+  "clean_up_tokenization_spaces": true,
+  "is_uroman": false,
+  "language": "spa",
+  "model_max_length": 1000000000000000019884624838656,
+  "normalize": true,
+  "pad_token": "7",
+  "phonemize": false,
+  "tokenizer_class": "VitsTokenizer",
+  "unk_token": "<unk>"
+}

mms-spa/vocab.json

@@ -0,0 +1,47 @@
+{
+  " ": 27,
+  "0": 5,
+  "1": 24,
+  "2": 36,
+  "3": 32,
+  "4": 12,
+  "5": 6,
+  "6": 44,
+  "7": 0,
+  "8": 8,
+  "9": 23,
+  "_": 22,
+  "a": 1,
+  "b": 31,
+  "c": 3,
+  "d": 29,
+  "e": 39,
+  "f": 25,
+  "g": 34,
+  "h": 19,
+  "i": 37,
+  "j": 33,
+  "k": 15,
+  "l": 35,
+  "m": 13,
+  "n": 20,
+  "o": 41,
+  "p": 9,
+  "q": 18,
+  "r": 43,
+  "s": 16,
+  "t": 26,
+  "u": 38,
+  "v": 2,
+  "x": 28,
+  "y": 10,
+  "z": 11,
+  "á": 17,
+  "é": 21,
+  "í": 30,
+  "ñ": 42,
+  "ó": 7,
+  "ú": 40,
+  "ü": 14,
+  "—": 4
+}