feat: restructure repo to match runtime, add missing piper voices, and update README/manifest

.gitattributes

@@ -39,3 +39,10 @@ tts/*.onnx filter=lfs diff=lfs merge=lfs -text
 tts/*.bin filter=lfs diff=lfs merge=lfs -text
 tts/*.tar.gz filter=lfs diff=lfs merge=lfs -text
 vad/*.onnx filter=lfs diff=lfs merge=lfs -text
+tts/piper_hi/*.onnx filter=lfs diff=lfs merge=lfs -text
+tts/piper_hi/*.tar.gz filter=lfs diff=lfs merge=lfs -text
+llm/gemma4/*.gguf filter=lfs diff=lfs merge=lfs -text
+stt/qwen3-asr/*.onnx filter=lfs diff=lfs merge=lfs -text
+tts/kokoro/model.onnx filter=lfs diff=lfs merge=lfs -text
+tts/kokoro/*.bin filter=lfs diff=lfs merge=lfs -text
+tts/kokoro/*.tar.gz filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,47 @@
 ---
 license: apache-2.0
+tags:
+- voice
+- stt
+- tts
+- llm
+- vox
+- real-time
+- edge-inference
+library_name: generic
 ---
+
+# Vox Models
+
+This repository serves as the official model host for **Vox**, a real-time, local-first voice-to-voice system. It contains specialized models for Voice Activity Detection (VAD), Speech-to-Text (STT), Large Language Models (LLM), and Text-to-Speech (TTS).
+
+## Directory Structure
+
+The structure of this repository exactly mirrors the runtime expectations of the Vox backend:
+
+```text
+.
+├── manifest.json            # Single source of truth for all models
+├── llm/
+│   └── gemma4/             # Large Language Models (GGUF)
+├── stt/
+│   └── qwen3-asr/          # Speech-to-Text (ONNX)
+│       └── tokenizer/      # STT Tokenizer configs
+├── tts/
+│   ├── kokoro/             # English TTS (Kokoro ONNX)
+│   └── piper_hi/           # Hindi TTS (Piper ONNX)
+└── vad/
+    └── ten_vad.onnx        # Voice Activity Detection (ONNX)
+```
+
+## Manifest
+
+The `manifest.json` file in the root directory provides metadata for automated management, including:
+- Relative file paths
+- Exact byte sizes
+- SHA256 hashes for integrity verification
+- Archive markers for compressed assets (e.g., `espeak-ng-data`)
+
+## Usage
+
+These models are intended to be downloaded and managed by the Vox application runtime. For manual use, ensure you have [Git LFS](https://git-lfs.github.com/) installed to correctly retrieve the large model weights.

manifests/manifest.json → manifest.json

@@ -1,6 +1,6 @@
 {
   "version": "1.0.0",
-  "total_size_bytes": 4924726403,
+  "total_size_bytes": 5008946279,
   "models": [
     {
       "id": "ten_vad",
@@ -10,82 +10,113 @@
     },
     {
       "id": "stt_conv_frontend",
-      "path": "stt/conv_frontend.onnx",
+      "path": "stt/qwen3-asr/conv_frontend.onnx",
       "size": 44148281,
-      "sha256": "d22dc4423e0940e49884e903d2ea2f7e5567c14fc1aed97e4e26d6b8f208ef9e"
+      "sha256": "63f8124374825bbde0c0f94d85426cca753cbdd5060085b1233463007165c8d3"
     },
     {
       "id": "stt_encoder",
-      "path": "stt/encoder.int8.onnx",
+      "path": "stt/qwen3-asr/encoder.int8.onnx",
       "size": 182491662,
-      "sha256": "60748d3e6744a57c9c91e1b17424a6c2990567e8adceb0783940c03ed98fa9d9"
+      "sha256": "77845dcff9a40ce1327a0ad4c55966c6181aed438c9e56e3d3535c1132301ef6"
     },
     {
       "id": "stt_decoder",
-      "path": "stt/decoder.int8.onnx",
+      "path": "stt/qwen3-asr/decoder.int8.onnx",
       "size": 755914231,
-      "sha256": "4f6885be5959ae26af3089d38ee7972c5fafbeeb1cf8d5e76eab6d8b61ca5771"
+      "sha256": "1bb2a998a84d5422af985c00af8f169fa433a8df4df0b26ab4040095141f88c2"
     },
     {
       "id": "stt_vocab",
-      "path": "stt/vocab.json",
+      "path": "stt/qwen3-asr/tokenizer/vocab.json",
       "size": 2776833,
       "sha256": "ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910"
     },
     {
       "id": "stt_merges",
-      "path": "stt/merges.txt",
+      "path": "stt/qwen3-asr/tokenizer/merges.txt",
       "size": 1671853,
       "sha256": "8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5"
     },
     {
       "id": "stt_config",
-      "path": "stt/tokenizer_config.json",
+      "path": "stt/qwen3-asr/tokenizer/tokenizer_config.json",
       "size": 12487,
       "sha256": "4942d005604266809309cabc9f4e9cb89ce855d59b14681fdc0e1cc62ea26c4c"
     },
     {
       "id": "llm_gemma_4_q4_k_m",
-      "path": "llm/google_gemma-4-E2B-it-Q4_K_M.gguf",
+      "path": "llm/gemma4/google_gemma-4-E2B-it-Q4_K_M.gguf",
       "size": 3462678272,
       "sha256": "b5310340b3a23d31655d7119d100d5df1b2d8ee17b3ca8b0a23ad7e9eb5fa705"
     },
     {
       "id": "tts_kokoro_onnx",
-      "path": "tts/kokoro-v0.19.onnx",
+      "path": "tts/kokoro/model.onnx",
       "size": 345555491,
-      "sha256": "10ff414106a038ce7e9e0126c6461e4dc8a86efaa89dc91d2009d69fe635e339"
+      "sha256": "6b64b1473beb7efa5704e821a4384839b722bdc671ef7300ad640a2f301a8c0b"
     },
     {
       "id": "tts_kokoro_voices",
-      "path": "tts/kokoro-voices.bin",
+      "path": "tts/kokoro/voices.bin",
       "size": 5755904,
-      "sha256": "a372c67b056ef0b695c375d39b99630d23fb07ad4c8d87aa32a19a62fca523ad"
+      "sha256": "4c5c6bde45060417d61978970aa7684b25e8d3d7cc5349a4f3222474899a8388"
     },
     {
       "id": "tts_kokoro_tokens",
-      "path": "tts/kokoro-tokens.txt",
+      "path": "tts/kokoro/tokens.txt",
       "size": 1078,
       "sha256": "4f31c71282d14af4e926cd12462078fe9d20d00c589e63fe2750a8f56d6d7f7b"
     },
     {
-      "id": "tts_espeak_ng_data",
-      "path": "tts/espeak-ng-data.tar.gz",
+      "id": "tts_kokoro_espeak_ng_data",
+      "path": "tts/kokoro/espeak-ng-data.tar.gz",
       "size": 8990857,
       "sha256": "7ddfb7247e98108baeab2a3f9c79c29247e58ae7d60d837b32e28999f555bf8d",
       "archive": "tar.gz"
     },
     {
-      "id": "tts_hi_piper_onnx",
-      "path": "tts/hi_IN-priyamvada-medium.onnx",
+      "id": "tts_hi_pratham_onnx",
+      "path": "tts/piper_hi/hi_IN-pratham-medium.onnx",
+      "size": 63516050,
+      "sha256": "169964b0871667f6793416d4b35e97357a68ba1ad01df8580c28048989ee7693"
+    },
+    {
+      "id": "tts_hi_pratham_config",
+      "path": "tts/piper_hi/hi_IN-pratham-medium.onnx.json",
+      "size": 4970,
+      "sha256": "b68edd2cd7950dd436314013b7cd12e9699e5a3f6fe5af5af94294cf6aa7b9fd"
+    },
+    {
+      "id": "tts_hi_priyamvada_onnx",
+      "path": "tts/piper_hi/hi_IN-priyamvada-medium.onnx",
       "size": 63145178,
-      "sha256": "8871f3e07adb6ca490f8dbcd3956a8647c53c35b5d0a1c2a8d097b3bf721a31b"
+      "sha256": "91f62f46662fad367a977a48abd30ee1a7f178a6f2f3e3930361a8f6c0a92421"
     },
     {
-      "id": "tts_hi_piper_config",
-      "path": "tts/hi_IN-priyamvada-medium.onnx.json",
+      "id": "tts_hi_priyamvada_config",
+      "path": "tts/piper_hi/hi_IN-priyamvada-medium.onnx.json",
       "size": 4973,
       "sha256": "5efc0ccf7529f3528996d46e0fac1f969f681d44a8e55bfa6236ff8841b5d52d"
+    },
+    {
+      "id": "tts_hi_rohan_onnx",
+      "path": "tts/piper_hi/hi_IN-rohan-medium.onnx",
+      "size": 62950044,
+      "sha256": "b65dc80fb34d9dcd1cf684cb297966a34983bbc93bb1696fe207f32b0b33a091"
+    },
+    {
+      "id": "tts_hi_rohan_config",
+      "path": "tts/piper_hi/hi_IN-rohan-medium.onnx.json",
+      "size": 5041,
+      "sha256": "07b9ae19bd0bac7fbbc99f7ee69c91245eb5470e926632c31fc0c50ba653c817"
+    },
+    {
+      "id": "tts_piper_hi_espeak_ng_data",
+      "path": "tts/piper_hi/espeak-ng-data.tar.gz",
+      "size": 8990869,
+      "sha256": "5d26294483bff947820b8ebf55fde437622c7c542eb104649e29626ab1763524",
+      "archive": "tar.gz"
     }
   ]
 }

tts/piper_hi/espeak-ng-data.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d26294483bff947820b8ebf55fde437622c7c542eb104649e29626ab1763524
+size 8990869

tts/piper_hi/hi_IN-pratham-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:169964b0871667f6793416d4b35e97357a68ba1ad01df8580c28048989ee7693
+size 63516050

tts/piper_hi/hi_IN-pratham-medium.onnx.json

@@ -0,0 +1,502 @@
+{
+  "dataset": "pratham",
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "hi"
+  },
+  "language": {
+    "code": "hi_IN",
+    "family": "hi",
+    "region": "IN",
+    "name_native": "हिन्दी",
+    "name_english": "Hindi",
+    "country_english": "India"
+  },
+  "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"
+}

tts/piper_hi/hi_IN-rohan-medium.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65dc80fb34d9dcd1cf684cb297966a34983bbc93bb1696fe207f32b0b33a091
+size 62950044

tts/piper_hi/hi_IN-rohan-medium.onnx.json

@@ -0,0 +1,512 @@
+{
+  "audio": {
+    "sample_rate": 22050,
+    "quality": "medium"
+  },
+  "espeak": {
+    "voice": "hi"
+  },
+  "phoneme_type": "espeak",
+  "piper_version": "1.3.0",
+  "num_symbols": 256,
+  "num_speakers": 1,
+  "inference": {
+    "noise_scale": 0.667,
+    "length_scale": 1.0,
+    "noise_w": 0.8
+  },
+  "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
+    ],
+    "g": [
+      154
+    ],
+    "ʦ": [
+      155
+    ],
+    "X": [
+      156
+    ],
+    "̝": [
+      157
+    ],
+    "̊": [
+      158
+    ],
+    "ɝ": [
+      159
+    ],
+    "ʷ": [
+      160
+    ]
+  },
+  "language": {
+    "code": "hi_IN",
+    "family": "hi",
+    "region": "IN",
+    "name_native": "हिन्दी",
+    "name_english": "Hindi",
+    "country_english": "India"
+  },
+  "dataset": "rohan"
+}