--- language: - multilingual license: apache-2.0 author: DarkPs library_name: transformers tags: - ice-012-audio - text-to-voice - voice-to-voice pipeline_tag: text-to-speech ---
# ❄️ ICE-012 Audio ### Multilingual Text-to-Speech & Voice Cloning

IceAudio

**[DarkPs on Hugging Face](https://huggingface.co/darkps)** · **[dark.ps](https://dark.ps)**
![ICE-012 Audio](assets/ice012_cover.png) ICE-012 Audio is a multilingual text-to-speech model with streaming output and voice-cloning support. The supplied source documentation defines **400+ accepted language names/variants mapped to 654 unique IDs**. ## Highlights | Capability | Details | |---|---| | Multilingual | 400+ accepted language names / variants | | Language IDs | 654 unique IDs | | Text to Speech | Streaming output | | Voice Cloning | Reference-audio based cloning | | Voice controls | Gender, age, pitch, accent, style, speed | | License | Apache-2.0 | ## Language Coverage ![ICE-012 Audio language coverage statistics](assets/language_stats.png) The source mapping includes dialect aliases, regional variants, minority/local languages, and duplicate IDs where they occur in the original source DarkPs. ## Media ### Model Preview ### Test Audio The four WAV files in [`test/`](test/) are repository test samples. - [Sample 01](test/MrBest.mp3) - [Sample 02](test/Molham.mp3) - [Sample 03](test/oshasalah.mp3) - [Sample 04](test/Wissam.mp3) > These WAV files are test assets included for repository/media validation; they are not claimed here as generated model outputs. ## Usage Guide ## Tools | File | Description | |------|-------------| | `01_download_model.py` | Download and verify the model checkpoint | | `02_stream_tts.py` | Text-to-speech with streaming output | | `03_stream_voice_clone.py` | Voice cloning from a reference audio file | --- ## 01 — Download Model ```bash python 01_download_model.py --output ./ice-012-Audio ``` | Argument | Default | Description | |----------|---------|-------------| | `--output` | `./ice-012-Audio` | Directory to save the model | --- ## 02 — Text to Speech ```bash python 02_stream_tts.py --language "arabic" --gender female --style "young adult" --speed 1.0 --output out.wav python 02_stream_tts.py --text-file input.txt --language "en" --gender male --style "elderly, low pitch" python 02_stream_tts.py --language "egyptian lahgtna" --gender female --auto-voice ``` | Argument | Default | Description | |----------|---------|-------------| | `--model` | `./ice-012-Audio` | Path to model directory | | `--output` | `tts_stream.wav` | Output WAV file | | `--text-file` | — | Read text from file (overrides TEXT constant) | | `--language` | `Arabic` | Language name or 2–3 letter ID (see full list below) | | `--gender` | — | `male` or `female` | | `--style` | — | Age, pitch, accent — comma-separated (see options below) | | `--speed` | `1.0` | Speed multiplier | | `--auto-voice` | off | Let model choose voice automatically, ignores `--gender` and `--style` | --- ## 03 — Voice Clone ```bash python 03_stream_voice_clone.py --reference ref.wav --output clone.wav python 03_stream_voice_clone.py --reference ref.wav --text-file input.txt --reference-text "transcript" ``` | Argument | Default | Description | |----------|---------|-------------| | `--model` | `./ice-012-Audio` | Path to model directory | | `--reference` | required | Reference audio file (WAV) | | `--output` | `clone_stream.wav` | Output WAV file | | `--text-file` | — | Read text from file (overrides TEXT constant) | | `--reference-text` | — | Transcript of the reference audio (improves quality) | | `--speed` | `1.0` | Speed multiplier | > Use only audio you own or have explicit permission to process. --- ## Voice Options ### Gender | Value | Description | |-------|-------------| | `male` | Male voice | | `female` | Female voice | ### Age (`--style`) | Value | Description | |-------|-------------| | `child` | Child voice (~5–10) | | `teenager` | Teen voice (~13–17) | | `young adult` | 20s–30s | | `middle-aged` | 40s–50s | | `elderly` | 60+ | ### Pitch (`--style`) | Value | Description | |-------|-------------| | `very low pitch` | Deepest | | `low pitch` | | | `moderate pitch` | Neutral / default | | `high pitch` | | | `very high pitch` | Highest | ### Style (`--style`) | Value | Description | |-------|-------------| | `whisper` | Whispered voice | ### Accent (`--style`) | Value | |-------| | `american accent` | | `british accent` | | `australian accent` | | `canadian accent` | | `indian accent` | | `chinese accent` | | `japanese accent` | | `korean accent` | | `russian accent` | | `portuguese accent` | ### Speed (`--speed`) | Value | Description | |-------|-------------| | `0.5` | Half speed | | `1.0` | Normal (default) | | `1.5` | 1.5× | | `2.0` | Double speed | ### Combining options `--style` accepts a comma-separated list: ```bash --gender female --style "young adult, high pitch" --gender male --style "elderly, low pitch" --gender female --style "teenager, british accent" --gender male --style "middle-aged, american accent, moderate pitch" ``` --- ## Language Parameter The `--language` argument accepts **two formats** — both produce identical results: | Format | Example | Notes | |--------|---------|-------| | Full name | `"palestinian lahgtna"` | Case-insensitive | | Short ID | `"ps"` | 2–3 letter code | If the value is not recognised, the model falls back to language-agnostic mode and prints a warning — it does **not** raise an error. ```python # These three are identical: language="palestinian lahgtna" language="Palestinian Lahgtna" language="ps" ``` --- ## Supported languages, dialects, and variants The current `modeling_iceAudio.py` defines **400+ accepted language names/variants** in `LANG_NAME_TO_ID`, corresponding to **654 unique IDs**. The tables below reproduce the source mapping without removing dialects, regional variants, minority languages, or other entries. > **Source fidelity:** IDs and names are kept exactly as defined by the current Python source. The source contains several duplicate IDs; those entries are preserved rather than silently changed. ### Dialect aliases | Name | ID | |---|---| | Egyptian Lahgtna | `eg` | | Saudi Lahgtna | `sa` | | Moroccan Lahgtna | `ma` | | Bahraini Lahgtna | `bh` | | Sudanese Lahgtna | `sd` | | Iraqi Lahgtna | `iq` | | Lebanese Lahgtna | `lb` | | Syrian Lahgtna | `sy` | | Libyan Lahgtna | `ly` | | Palestinian Lahgtna | `ps` | | Tunisian Lahgtna | `tn` | | Algerian Lahgtna | `dz` | | Yemeni Lahgtna | `ye` | ### Complete `LANG_NAME_TO_ID` mapping | # | Display name | Accepted language name | ID | |---:|---|---|---| | 1 | Egyptian Lahgtna | `egyptian lahgtna` | `eg` | | 2 | Saudi Lahgtna | `saudi lahgtna` | `sa` | | 3 | Moroccan Lahgtna | `moroccan lahgtna` | `ma` | | 4 | Bahraini Lahgtna | `bahraini lahgtna` | `bh` | | 5 | Sudanese Lahgtna | `sudanese lahgtna` | `sd` | | 6 | Iraqi Lahgtna | `iraqi lahgtna` | `iq` | | 7 | Lebanese Lahgtna | `lebanese lahgtna` | `lb` | | 8 | Syrian Lahgtna | `syrian lahgtna` | `sy` | | 9 | Libyan Lahgtna | `libyan lahgtna` | `ly` | | 10 | Palestinian Lahgtna | `palestinian lahgtna` | `ps` | | 11 | Tunisian Lahgtna | `tunisian lahgtna` | `tn` | | 12 | Algerian Lahgtna | `algerian lahgtna` | `dz` | | 13 | Yemeni Lahgtna | `yemeni lahgtna` | `ye` | | 14 | Abadi | `abadi` | `kbt` | | 15 | Abkhazian | `abkhazian` | `ab` | | 16 | Abron | `abron` | `abr` | | 17 | Abua | `abua` | `abn` | | 18 | Adamawa Fulfulde | `adamawa fulfulde` | `fub` | | 19 | Adyghe | `adyghe` | `ady` | | 20 | Afade | `afade` | `aal` | | 21 | Afrikaans | `afrikaans` | `af` | | 22 | Agwagwune | `agwagwune` | `yay` | | 23 | Aja (Benin) | `aja (benin)` | `ajg` | | 24 | Akebu | `akebu` | `keu` | | 25 | Alago | `alago` | `ala` | | 26 | Albanian | `albanian` | `sq` | | 27 | Algerian Arabic | `algerian arabic` | `arq` | | 28 | Algerian Saharan Arabic | `algerian saharan arabic` | `aao` | | 29 | Ambo-Pasco Quechua | `ambo-pasco quechua` | `qva` | | 30 | Ambonese Malay | `ambonese malay` | `abs` | | 31 | Amdo Tibetan | `amdo tibetan` | `adx` | | 32 | Amharic | `amharic` | `am` | | 33 | Anaang | `anaang` | `anw` | | 34 | Angika | `angika` | `anp` | | 35 | Antankarana Malagasy | `antankarana malagasy` | `xmv` | | 36 | Aragonese | `aragonese` | `an` | | 37 | Arbëreshë Albanian | `arbëreshë albanian` | `aae` | | 38 | Arequipa-La Unión Quechua | `arequipa-la unión quechua` | `qxu` | | 39 | Armenian | `armenian` | `hy` | | 40 | Ashe | `ashe` | `ahs` | | 41 | Ashéninka Perené | `ashéninka perené` | `prq` | | 42 | Askopan | `askopan` | `eiv` | | 43 | Assamese | `assamese` | `as` | | 44 | Asturian | `asturian` | `ast` | | 45 | Atayal | `atayal` | `tay` | | 46 | Awak | `awak` | `awo` | | 47 | Ayacucho Quechua | `ayacucho quechua` | `quy` | | 48 | Azerbaijani | `azerbaijani` | `az` | | 49 | Baatonum | `baatonum` | `bba` | | 50 | Bacama | `bacama` | `bcy` | | 51 | Bade | `bade` | `bde` | | 52 | Bafia | `bafia` | `ksf` | | 53 | Bafut | `bafut` | `bfd` | | 54 | Bagirmi Fulfulde | `bagirmi fulfulde` | `fui` | | 55 | Bago-Kusuntu | `bago-kusuntu` | `bqg` | | 56 | Baharna Arabic | `baharna arabic` | `abv` | | 57 | Bakoko | `bakoko` | `bkh` | | 58 | Balanta-Ganja | `balanta-ganja` | `bjt` | | 59 | Balti | `balti` | `bft` | | 60 | Bamenyam | `bamenyam` | `bce` | | 61 | Bamun | `bamun` | `bax` | | 62 | Bangwinji | `bangwinji` | `bsj` | | 63 | Banjar | `banjar` | `bjn` | | 64 | Bankon | `bankon` | `abb` | | 65 | Baoulé | `baoulé` | `bci` | | 66 | Bara Malagasy | `bara malagasy` | `bhr` | | 67 | Barok | `barok` | `bjk` | | 68 | Basa (Cameroon) | `basa (cameroon)` | `bas` | | 69 | Basa (Nigeria) | `basa (nigeria)` | `bzw` | | 70 | Bashkir | `bashkir` | `ba` | | 71 | Basque | `basque` | `eu` | | 72 | Batak Mandailing | `batak mandailing` | `btm` | | 73 | Batanga | `batanga` | `bnm` | | 74 | Bateri | `bateri` | `btv` | | 75 | Bats | `bats` | `bbl` | | 76 | Bayot | `bayot` | `bda` | | 77 | Bebele | `bebele` | `beb` | | 78 | Belarusian | `belarusian` | `be` | | 79 | Bengali | `bengali` | `bn` | | 80 | Betawi | `betawi` | `bew` | | 81 | Bhili | `bhili` | `bhb` | | 82 | Bhojpuri | `bhojpuri` | `bho` | | 83 | Bilur | `bilur` | `bxf` | | 84 | Bima | `bima` | `bhp` | | 85 | Bodo | `bodo` | `brx` | | 86 | Boghom | `boghom` | `bux` | | 87 | Bokyi | `bokyi` | `bky` | | 88 | Bomu | `bomu` | `bmq` | | 89 | Bondei | `bondei` | `bou` | | 90 | Borgu Fulfulde | `borgu fulfulde` | `fue` | | 91 | Bosnian | `bosnian` | `bs` | | 92 | Brahui | `brahui` | `brh` | | 93 | Braj | `braj` | `bra` | | 94 | Breton | `breton` | `br` | | 95 | Buduma | `buduma` | `bdm` | | 96 | Buginese | `buginese` | `bug` | | 97 | Bukharic | `bukharic` | `bhh` | | 98 | Bulgarian | `bulgarian` | `bg` | | 99 | Bulu (Cameroon) | `bulu (cameroon)` | `bum` | | 100 | Bundeli | `bundeli` | `bns` | | 101 | Bunun | `bunun` | `bnn` | | 102 | Bura-Pabir | `bura-pabir` | `bwr` | | 103 | Burak | `burak` | `bys` | | 104 | Burmese | `burmese` | `my` | | 105 | Burushaski | `burushaski` | `bsk` | | 106 | Cacaloxtepec Mixtec | `cacaloxtepec mixtec` | `miu` | | 107 | Cajatambo North Lima Quechua | `cajatambo north lima quechua` | `qvl` | | 108 | Cakfem-Mushere | `cakfem-mushere` | `cky` | | 109 | Cameroon Pidgin | `cameroon pidgin` | `wes` | | 110 | Campidanese Sardinian | `campidanese sardinian` | `sro` | | 111 | Cantonese | `cantonese` | `yue` | | 112 | Catalan | `catalan` | `ca` | | 113 | Cebuano | `cebuano` | `ceb` | | 114 | Cen | `cen` | `cen` | | 115 | Central Kurdish | `central kurdish` | `ckb` | | 116 | Central Nahuatl | `central nahuatl` | `nhn` | | 117 | Central Pame | `central pame` | `pbs` | | 118 | Central Pashto | `central pashto` | `pst` | | 119 | Central Puebla Nahuatl | `central puebla nahuatl` | `ncx` | | 120 | Central Tarahumara | `central tarahumara` | `tar` | | 121 | Central Yupik | `central yupik` | `esu` | | 122 | Central-Eastern Niger Fulfulde | `central-eastern niger fulfulde` | `fuq` | | 123 | Chadian Arabic | `chadian arabic` | `shu` | | 124 | Chichewa | `chichewa` | `ny` | | 125 | Chichicapan Zapotec | `chichicapan zapotec` | `zpv` | | 126 | Chiga | `chiga` | `cgg` | | 127 | Chimalapa Zoque | `chimalapa zoque` | `zoh` | | 128 | Chimborazo Highland Quichua | `chimborazo highland quichua` | `qug` | | 129 | Chinese | `chinese` | `zh` | | 130 | Chiquián Ancash Quechua | `chiquián ancash quechua` | `qxa` | | 131 | Chitwania Tharu | `chitwania tharu` | `the` | | 132 | Chokwe | `chokwe` | `cjk` | | 133 | Chuvash | `chuvash` | `cv` | | 134 | Cibak | `cibak` | `ckl` | | 135 | Coastal Konjo | `coastal konjo` | `kjc` | | 136 | Copainalá Zoque | `copainalá zoque` | `zoc` | | 137 | Cornish | `cornish` | `kw` | | 138 | Corongo Ancash Quechua | `corongo ancash quechua` | `qwa` | | 139 | Croatian | `croatian` | `hr` | | 140 | Cross River Mbembe | `cross river mbembe` | `mfn` | | 141 | Cuyamecalco Mixtec | `cuyamecalco mixtec` | `xtu` | | 142 | Czech | `czech` | `cs` | | 143 | Dadiya | `dadiya` | `dbd` | | 144 | Dagbani | `dagbani` | `dag` | | 145 | Dameli | `dameli` | `dml` | | 146 | Danish | `danish` | `da` | | 147 | Dargwa | `dargwa` | `dar` | | 148 | Dazaga | `dazaga` | `dzg` | | 149 | Deccan | `deccan` | `dcc` | | 150 | Degema | `degema` | `deg` | | 151 | Dera (Nigeria) | `dera (nigeria)` | `kna` | | 152 | Dghwede | `dghwede` | `dgh` | | 153 | Dhatki | `dhatki` | `mki` | | 154 | Dhivehi | `dhivehi` | `dv` | | 155 | Dhofari Arabic | `dhofari arabic` | `adf` | | 156 | Dijim-Bwilim | `dijim-bwilim` | `cfa` | | 157 | Dogri | `dogri` | `dgo` | | 158 | Domaaki | `domaaki` | `dmk` | | 159 | Dotyali | `dotyali` | `dty` | | 160 | Duala | `duala` | `dua` | | 161 | Dutch | `dutch` | `nl` | | 162 | Dũya | `dũya` | `ldb` | | 163 | Dyula | `dyula` | `dyu` | | 164 | Eastern Balochi | `eastern balochi` | `bgp` | | 165 | Eastern Bolivian Guaraní | `eastern bolivian guaraní` | `gui` | | 166 | Eastern Egyptian Bedawi Arabic | `eastern egyptian bedawi arabic` | `avl` | | 167 | Eastern Krahn | `eastern krahn` | `kqo` | | 168 | Eastern Mari | `eastern mari` | `mhr` | | 169 | Eastern Yiddish | `eastern yiddish` | `ydd` | | 170 | Ebrié | `ebrié` | `ebr` | | 171 | Eggon | `eggon` | `ego` | | 172 | Egyptian Arabic | `egyptian arabic` | `arz` | | 173 | Ejagham | `ejagham` | `etu` | | 174 | Eleme | `eleme` | `elm` | | 175 | Eloyi | `eloyi` | `afo` | | 176 | Embu | `embu` | `ebu` | | 177 | English | `english` | `en` | | 178 | Erzya | `erzya` | `myv` | | 179 | Esan | `esan` | `ish` | | 180 | Esperanto | `esperanto` | `eo` | | 181 | Estonian | `estonian` | `et` | | 182 | Eton (Cameroon) | `eton (cameroon)` | `eto` | | 183 | Ewondo | `ewondo` | `ewo` | | 184 | Extremaduran | `extremaduran` | `ext` | | 185 | Fang (Equatorial Guinea) | `fang (equatorial guinea)` | `fan` | | 186 | Fanti | `fanti` | `fat` | | 187 | Farefare | `farefare` | `gur` | | 188 | Fe'fe' | `fe'fe'` | `fmp` | | 189 | Filipino | `filipino` | `fil` | | 190 | Filomena Mata-Coahuitlán Totonac | `filomena mata-coahuitlán totonac` | `tlp` | | 191 | Finnish | `finnish` | `fi` | | 192 | Fipa | `fipa` | `fip` | | 193 | French | `french` | `fr` | | 194 | Fulah | `fulah` | `ff` | | 195 | Galician | `galician` | `gl` | | 196 | Gambian Wolof | `gambian wolof` | `wof` | | 197 | Ganda | `ganda` | `lg` | | 198 | Garhwali | `garhwali` | `gbm` | | 199 | Gawar-Bati | `gawar-bati` | `gwt` | | 200 | Gawri | `gawri` | `gwc` | | 201 | Gbagyi | `gbagyi` | `gbr` | | 202 | Gbari | `gbari` | `gby` | | 203 | Geji | `geji` | `gyz` | | 204 | Gen | `gen` | `gej` | | 205 | Georgian | `georgian` | `ka` | | 206 | German | `german` | `de` | | 207 | Geser-Gorom | `geser-gorom` | `ges` | | 208 | Gheg Albanian | `gheg albanian` | `aln` | | 209 | Ghomálá' | `ghomálá'` | `bbj` | | 210 | Gidar | `gidar` | `gid` | | 211 | Glavda | `glavda` | `glw` | | 212 | Goan Konkani | `goan konkani` | `gom` | | 213 | Goaria | `goaria` | `gig` | | 214 | Goemai | `goemai` | `ank` | | 215 | Gola | `gola` | `gol` | | 216 | Greek | `greek` | `el` | | 217 | Guarani | `guarani` | `gn` | | 218 | Guduf-Gava | `guduf-gava` | `gdf` | | 219 | Guerrero Amuzgo | `guerrero amuzgo` | `amu` | | 220 | Gujarati | `gujarati` | `gu` | | 221 | Gujari | `gujari` | `gju` | | 222 | Gulf Arabic | `gulf arabic` | `afb` | | 223 | Gurgula | `gurgula` | `ggg` | | 224 | Gusii | `gusii` | `guz` | | 225 | Gusilay | `gusilay` | `gsl` | | 226 | Gweno | `gweno` | `gwe` | | 227 | Güilá Zapotec | `güilá zapotec` | `ztu` | | 228 | Hadothi | `hadothi` | `hoj` | | 229 | Hahon | `hahon` | `hah` | | 230 | Haitian | `haitian` | `ht` | | 231 | Hakha Chin | `hakha chin` | `cnh` | | 232 | Hakö | `hakö` | `hao` | | 233 | Halia | `halia` | `hla` | | 234 | Hausa | `hausa` | `ha` | | 235 | Hawaiian | `hawaiian` | `haw` | | 236 | Hazaragi | `hazaragi` | `haz` | | 237 | Hebrew | `hebrew` | `he` | | 238 | Hemba | `hemba` | `hem` | | 239 | Herero | `herero` | `hz` | | 240 | Highland Konjo | `highland konjo` | `kjk` | | 241 | Hijazi Arabic | `hijazi arabic` | `acw` | | 242 | Hindi | `hindi` | `hi` | | 243 | Huarijio | `huarijio` | `var` | | 244 | Huautla Mazatec | `huautla mazatec` | `mau` | | 245 | Huaxcaleca Nahuatl | `huaxcaleca nahuatl` | `nhq` | | 246 | Huba | `huba` | `hbb` | | 247 | Huitepec Mixtec | `huitepec mixtec` | `mxs` | | 248 | Hula | `hula` | `hul` | | 249 | Hungarian | `hungarian` | `hu` | | 250 | Hunjara-Kaina Ke | `hunjara-kaina ke` | `hkk` | | 251 | Hwana | `hwana` | `hwo` | | 252 | Ibibio | `ibibio` | `ibb` | | 253 | Icelandic | `icelandic` | `is` | | 254 | Idakho-Isukha-Tiriki | `idakho-isukha-tiriki` | `ida` | | 255 | Idoma | `idoma` | `idu` | | 256 | Igbo | `igbo` | `ig` | | 257 | Igo | `igo` | `ahl` | | 258 | Ikposo | `ikposo` | `kpo` | | 259 | Ikwere | `ikwere` | `ikw` | | 260 | Imbabura Highland Quichua | `imbabura highland quichua` | `qvi` | | 261 | Indonesian | `indonesian` | `id` | | 262 | Indus Kohistani | `indus kohistani` | `mvy` | | 263 | Interlingua (International Auxiliary Language Association) | `interlingua (international auxiliary language association)` | `ia` | | 264 | Inupiaq | `inupiaq` | `ik` | | 265 | Irish | `irish` | `ga` | | 266 | Iron Ossetic | `iron ossetic` | `os` | | 267 | Isekiri | `isekiri` | `its` | | 268 | Isoko | `isoko` | `iso` | | 269 | Italian | `italian` | `it` | | 270 | Ito | `ito` | `itw` | | 271 | Itzá | `itzá` | `itz` | | 272 | Ixtayutla Mixtec | `ixtayutla mixtec` | `vmj` | | 273 | Izon | `izon` | `ijc` | | 274 | Jambi Malay | `jambi malay` | `jax` | | 275 | Japanese | `japanese` | `ja` | | 276 | Jaqaru | `jaqaru` | `jqr` | | 277 | Jauja Wanca Quechua | `jauja wanca quechua` | `qxw` | | 278 | Jaunsari | `jaunsari` | `jns` | | 279 | Javanese | `javanese` | `jv` | | 280 | Jiba | `jiba` | `juo` | | 281 | Jju | `jju` | `kaj` | | 282 | Judeo-Moroccan Arabic | `judeo-moroccan arabic` | `aju` | | 283 | Juxtlahuaca Mixtec | `juxtlahuaca mixtec` | `vmc` | | 284 | Kabardian | `kabardian` | `kbd` | | 285 | Kabras | `kabras` | `lkb` | | 286 | Kabuverdianu | `kabuverdianu` | `kea` | | 287 | Kabyle | `kabyle` | `kab` | | 288 | Kachi Koli | `kachi koli` | `gjk` | | 289 | Kairak | `kairak` | `ckr` | | 290 | Kalabari | `kalabari` | `ijn` | | 291 | Kalasha | `kalasha` | `kls` | | 292 | Kalenjin | `kalenjin` | `kln` | | 293 | Kalkoti | `kalkoti` | `xka` | | 294 | Kamba | `kamba` | `kam` | | 295 | Kamo | `kamo` | `kcq` | | 296 | Kanauji | `kanauji` | `bjj` | | 297 | Kanembu | `kanembu` | `kbl` | | 298 | Kannada | `kannada` | `kn` | | 299 | Karekare | `karekare` | `kai` | | 300 | Kashmiri | `kashmiri` | `ks` | | 301 | Kathoriya Tharu | `kathoriya tharu` | `tkt` | | 302 | Kati | `kati` | `bsh` | | 303 | Kazakh | `kazakh` | `kk` | | 304 | Keiyo | `keiyo` | `eyo` | | 305 | Khams Tibetan | `khams tibetan` | `khg` | | 306 | Khana | `khana` | `ogo` | | 307 | Khetrani | `khetrani` | `xhe` | | 308 | Khmer | `khmer` | `km` | | 309 | Khowar | `khowar` | `khw` | | 310 | Kinga | `kinga` | `zga` | | 311 | Kinnauri | `kinnauri` | `kfk` | | 312 | Kinyarwanda | `kinyarwanda` | `rw` | | 313 | Kirghiz | `kirghiz` | `ky` | | 314 | Kirya-Konzəl | `kirya-konzəl` | `fkk` | | 315 | Kochila Tharu | `kochila tharu` | `thq` | | 316 | Kohistani Shina | `kohistani shina` | `plk` | | 317 | Kohumono | `kohumono` | `bcs` | | 318 | Kok Borok | `kok borok` | `trp` | | 319 | Kol (Papua New Guinea) | `kol (papua new guinea)` | `kol` | | 320 | Kom (Cameroon) | `kom (cameroon)` | `bkm` | | 321 | Koma | `koma` | `kmy` | | 322 | Konkani | `konkani` | `knn` | | 323 | Konzo | `konzo` | `koo` | | 324 | Korean | `korean` | `ko` | | 325 | Korwa | `korwa` | `kfp` | | 326 | Kota (India) | `kota (india)` | `kfe` | | 327 | Koti | `koti` | `eko` | | 328 | Kuanua | `kuanua` | `ksd` | | 329 | Kuanyama | `kuanyama` | `kj` | | 330 | Kui (India) | `kui (india)` | `uki` | | 331 | Kulung (Nigeria) | `kulung (nigeria)` | `bbu` | | 332 | Kuot | `kuot` | `kto` | | 333 | Kushi | `kushi` | `kuh` | | 334 | Kwambi | `kwambi` | `kwm` | | 335 | Kwasio | `kwasio` | `nmg` | | 336 | Lala-Roba | `lala-roba` | `lla` | | 337 | Lamang | `lamang` | `hia` | | 338 | Lao | `lao` | `lo` | | 339 | Larike-Wakasihu | `larike-wakasihu` | `alo` | | 340 | Lasi | `lasi` | `lss` | | 341 | Latgalian | `latgalian` | `ltg` | | 342 | Latvian | `latvian` | `lv` | | 343 | Levantine Arabic | `levantine arabic` | `apc` | | 344 | Liana-Seti | `liana-seti` | `ste` | | 345 | Liberia Kpelle | `liberia kpelle` | `xpe` | | 346 | Liberian English | `liberian english` | `lir` | | 347 | Libyan Arabic | `libyan arabic` | `ayl` | | 348 | Ligurian | `ligurian` | `lij` | | 349 | Lijili | `lijili` | `mgi` | | 350 | Lingala | `lingala` | `ln` | | 351 | Lithuanian | `lithuanian` | `lt` | | 352 | Loarki | `loarki` | `lrk` | | 353 | Logooli | `logooli` | `rag` | | 354 | Logudorese Sardinian | `logudorese sardinian` | `src` | | 355 | Loja Highland Quichua | `loja highland quichua` | `qvj` | | 356 | Loloda | `loloda` | `loa` | | 357 | Longuda | `longuda` | `lnu` | | 358 | Loxicha Zapotec | `loxicha zapotec` | `ztp` | | 359 | Luba-Lulua | `luba-lulua` | `lua` | | 360 | Luo | `luo` | `luo` | | 361 | Lushai | `lushai` | `lus` | | 362 | Luxembourgish | `luxembourgish` | `lb` | | 363 | Maasina Fulfulde | `maasina fulfulde` | `ffm` | | 364 | Maba (Chad) | `maba (chad)` | `mde` | | 365 | Macedo-Romanian | `macedo-romanian` | `rup` | | 366 | Macedonian | `macedonian` | `mk` | | 367 | Mada (Cameroon) | `mada (cameroon)` | `mxu` | | 368 | Mafa | `mafa` | `maf` | | 369 | Maithili | `maithili` | `mai` | | 370 | Malay | `malay` | `ms` | | 371 | Malayalam | `malayalam` | `ml` | | 372 | Mali | `mali` | `gcc` | | 373 | Malinaltepec Me'phaa | `malinaltepec me'phaa` | `tcf` | | 374 | Maltese | `maltese` | `mt` | | 375 | Mandara | `mandara` | `tbf` | | 376 | Mandjak | `mandjak` | `mfv` | | 377 | Manggarai | `manggarai` | `mqy` | | 378 | Manipuri | `manipuri` | `mni` | | 379 | Mansoanka | `mansoanka` | `msw` | | 380 | Manx | `manx` | `gv` | | 381 | Maori | `maori` | `mi` | | 382 | Marathi | `marathi` | `mr` | | 383 | Marghi Central | `marghi central` | `mrt` | | 384 | Marghi South | `marghi south` | `mfm` | | 385 | Maria (India) | `maria (india)` | `mrr` | | 386 | Marwari (Pakistan) | `marwari (pakistan)` | `mve` | | 387 | Masana | `masana` | `mcn` | | 388 | Masikoro Malagasy | `masikoro malagasy` | `msh` | | 389 | Matsés | `matsés` | `mcf` | | 390 | Mazaltepec Zapotec | `mazaltepec zapotec` | `zpy` | | 391 | Mazatlán Mazatec | `mazatlán mazatec` | `vmz` | | 392 | Mazatlán Mixe | `mazatlán mixe` | `mzl` | | 393 | Mbe | `mbe` | `mfo` | | 394 | Mbo (Cameroon) | `mbo (cameroon)` | `mbo` | | 395 | Mbum | `mbum` | `mdd` | | 396 | Medumba | `medumba` | `byv` | | 397 | Mekeo | `mekeo` | `mek` | | 398 | Meru | `meru` | `mer` | | 399 | Mesopotamian Arabic | `mesopotamian arabic` | `acm` | | 400 | Mewari | `mewari` | `mtr` | | 401 | Min Nan Chinese | `min nan chinese` | `nan` | | 402 | Mingrelian | `mingrelian` | `xmf` | | 403 | Mitlatongo Mixtec | `mitlatongo mixtec` | `vmm` | | 404 | Miya | `miya` | `mkf` | | 405 | Mokpwe | `mokpwe` | `bri` | | 406 | Moksha | `moksha` | `mdf` | | 407 | Mom Jango | `mom jango` | `ver` | | 408 | Mongolian | `mongolian` | `mn` | | 409 | Moroccan Arabic | `moroccan arabic` | `ary` | | 410 | Motu | `motu` | `meu` | | 411 | Mpiemo | `mpiemo` | `mcx` | | 412 | Mpumpong | `mpumpong` | `mgg` | | 413 | Mundang | `mundang` | `mua` | | 414 | Mungaka | `mungaka` | `mhk` | | 415 | Musey | `musey` | `mse` | | 416 | Musgu | `musgu` | `mug` | | 417 | Musi | `musi` | `mui` | | 418 | Naba | `naba` | `mne` | | 419 | Najdi Arabic | `najdi arabic` | `ars` | | 420 | Nalik | `nalik` | `nal` | | 421 | Nawdm | `nawdm` | `nmz` | | 422 | Ndonga | `ndonga` | `ng` | | 423 | Neapolitan | `neapolitan` | `nap` | | 424 | Nepali | `nepali` | `npi` | | 425 | Ngamo | `ngamo` | `nbh` | | 426 | Ngas | `ngas` | `anc` | | 427 | Ngiemboon | `ngiemboon` | `nnh` | | 428 | Ngizim | `ngizim` | `ngi` | | 429 | Ngomba | `ngomba` | `jgo` | | 430 | Ngombale | `ngombale` | `nla` | | 431 | Nigerian Fulfulde | `nigerian fulfulde` | `fuv` | | 432 | Nigerian Pidgin | `nigerian pidgin` | `pcm` | | 433 | Nimadi | `nimadi` | `noe` | | 434 | Nobiin | `nobiin` | `fia` | | 435 | North Mesopotamian Arabic | `north mesopotamian arabic` | `ayp` | | 436 | North Moluccan Malay | `north moluccan malay` | `max` | | 437 | Northern Betsimisaraka Malagasy | `northern betsimisaraka malagasy` | `bmm` | | 438 | Northern Hindko | `northern hindko` | `hno` | | 439 | Northern Kurdish | `northern kurdish` | `kmr` | | 440 | Northern Pame | `northern pame` | `pmq` | | 441 | Northern Pashto | `northern pashto` | `pbu` | | 442 | Northern Uzbek | `northern uzbek` | `uzn` | | 443 | Northwest Gbaya | `northwest gbaya` | `gya` | | 444 | Norwegian | `norwegian` | `no` | | 445 | Norwegian Bokmål | `norwegian bokmål` | `nb` | | 446 | Norwegian Nynorsk | `norwegian nynorsk` | `nn` | | 447 | Notsi | `notsi` | `ncf` | | 448 | Nyankpa | `nyankpa` | `yes` | | 449 | Nyungwe | `nyungwe` | `nyu` | | 450 | Nzanyi | `nzanyi` | `nja` | | 451 | Nüpode Huitoto | `nüpode huitoto` | `hux` | | 452 | Occitan | `occitan` | `oc` | | 453 | Od | `od` | `odk` | | 454 | Odia | `odia` | `ory` | | 455 | Odual | `odual` | `odu` | | 456 | Omani Arabic | `omani arabic` | `acx` | | 457 | Orizaba Nahuatl | `orizaba nahuatl` | `nlv` | | 458 | Orma | `orma` | `orc` | | 459 | Ormuri | `ormuri` | `oru` | | 460 | Oromo | `oromo` | `om` | | 461 | Pahari-Potwari | `pahari-potwari` | `phr` | | 462 | Paiwan | `paiwan` | `pwn` | | 463 | Panjabi | `panjabi` | `pa` | | 464 | Papuan Malay | `papuan malay` | `pmy` | | 465 | Parkari Koli | `parkari koli` | `kvx` | | 466 | Pedi | `pedi` | `nso` | | 467 | Pero | `pero` | `pip` | | 468 | Persian | `persian` | `fa` | | 469 | Petats | `petats` | `pex` | | 470 | Phalura | `phalura` | `phl` | | 471 | Piemontese | `piemontese` | `pms` | | 472 | Piya-Kwonci | `piya-kwonci` | `piy` | | 473 | Plateau Malagasy | `plateau malagasy` | `plt` | | 474 | Polish | `polish` | `pl` | | 475 | Poqomam | `poqomam` | `poc` | | 476 | Portuguese | `portuguese` | `pt` | | 477 | Pulaar | `pulaar` | `fuc` | | 478 | Pular | `pular` | `fuf` | | 479 | Puno Quechua | `puno quechua` | `qxp` | | 480 | Pushto | `pushto` | `ps` | | 481 | Pökoot | `pökoot` | `pko` | | 482 | Qaqet | `qaqet` | `byx` | | 483 | Quiotepec Chinantec | `quiotepec chinantec` | `chq` | | 484 | Rana Tharu | `rana tharu` | `thr` | | 485 | Rangi | `rangi` | `lag` | | 486 | Rapoisi | `rapoisi` | `kyx` | | 487 | Ratahan | `ratahan` | `rth` | | 488 | Rayón Zoque | `rayón zoque` | `zor` | | 489 | Romanian | `romanian` | `ro` | | 490 | Romansh | `romansh` | `rm` | | 491 | Rombo | `rombo` | `rof` | | 492 | Rotokas | `rotokas` | `roo` | | 493 | Rukai | `rukai` | `dru` | | 494 | Russian | `russian` | `ru` | | 495 | Sacapulteco | `sacapulteco` | `quv` | | 496 | Saidi Arabic | `saidi arabic` | `aec` | | 497 | Sakalava Malagasy | `sakalava malagasy` | `skg` | | 498 | Sakizaya | `sakizaya` | `szy` | | 499 | Saleman | `saleman` | `sau` | | 500 | Samba Daka | `samba daka` | `ccg` | | 501 | Samba Leko | `samba leko` | `ndi` | | 502 | San Felipe Otlaltepec Popoloca | `san felipe otlaltepec popoloca` | `pow` | | 503 | San Francisco Del Mar Huave | `san francisco del mar huave` | `hue` | | 504 | San Juan Atzingo Popoloca | `san juan atzingo popoloca` | `poe` | | 505 | San Martín Itunyoso Triqui | `san martín itunyoso triqui` | `trq` | | 506 | San Miguel El Grande Mixtec | `san miguel el grande mixtec` | `mig` | | 507 | Sansi | `sansi` | `ssi` | | 508 | Sanskrit | `sanskrit` | `sa` | | 509 | Santa Ana De Tusi Pasco Quechua | `santa ana de tusi pasco quechua` | `qxt` | | 510 | Santa Catarina Albarradas Zapotec | `santa catarina albarradas zapotec` | `ztn` | | 511 | Santali | `santali` | `sat` | | 512 | Santiago del Estero Quichua | `santiago del estero quichua` | `qus` | | 513 | Saposa | `saposa` | `sps` | | 514 | Saraiki | `saraiki` | `skr` | | 515 | Sardinian | `sardinian` | `sc` | | 516 | Saya | `saya` | `say` | | 517 | Sediq | `sediq` | `trv` | | 518 | Serbian | `serbian` | `sr` | | 519 | Seri | `seri` | `sei` | | 520 | Shina | `shina` | `scl` | | 521 | Shona | `shona` | `sn` | | 522 | Siar-Lak | `siar-lak` | `sjr` | | 523 | Sibe | `sibe` | `nco` | | 524 | Sicilian | `sicilian` | `scn` | | 525 | Sihuas Ancash Quechua | `sihuas ancash quechua` | `qws` | | 526 | Sikkimese | `sikkimese` | `sip` | | 527 | Sinaugoro | `sinaugoro` | `snc` | | 528 | Sindhi | `sindhi` | `sd` | | 529 | Sindhi Bhil | `sindhi bhil` | `sbn` | | 530 | Sinhala | `sinhala` | `si` | | 531 | Sinicahua Mixtec | `sinicahua mixtec` | `xti` | | 532 | Sipacapense | `sipacapense` | `qum` | | 533 | Siwai | `siwai` | `siw` | | 534 | Slovak | `slovak` | `sk` | | 535 | Slovenian | `slovenian` | `sl` | | 536 | Solos | `solos` | `sol` | | 537 | Somali | `somali` | `so` | | 538 | Soninke | `soninke` | `snk` | | 539 | South Giziga | `south giziga` | `giz` | | 540 | South Ucayali Ashéninka | `south ucayali ashéninka` | `cpy` | | 541 | Southeastern Nochixtlán Mixtec | `southeastern nochixtlán mixtec` | `mxy` | | 542 | Southern Betsimisaraka Malagasy | `southern betsimisaraka malagasy` | `bzc` | | 543 | Southern Pashto | `southern pashto` | `pbt` | | 544 | Southern Pastaza Quechua | `southern pastaza quechua` | `qup` | | 545 | Soyaltepec Mazatec | `soyaltepec mazatec` | `vmp` | | 546 | Spanish | `spanish` | `es` | | 547 | Standard Arabic | `standard arabic` | `arb` | | 548 | Standard Moroccan Tamazight | `standard moroccan tamazight` | `zgh` | | 549 | Sudanese Arabic | `sudanese arabic` | `apd` | | 550 | Sulka | `sulka` | `sua` | | 551 | Svan | `svan` | `sva` | | 552 | Swahili | `swahili` | `sw` | | 553 | Swedish | `swedish` | `sv` | | 554 | Tae' | `tae'` | `rob` | | 555 | Tahaggart Tamahaq | `tahaggart tamahaq` | `thv` | | 556 | Taita | `taita` | `dav` | | 557 | Tajik | `tajik` | `tg` | | 558 | Tamil | `tamil` | `ta` | | 559 | Tandroy-Mahafaly Malagasy | `tandroy-mahafaly malagasy` | `tdx` | | 560 | Tangale | `tangale` | `tan` | | 561 | Tanosy Malagasy | `tanosy malagasy` | `txy` | | 562 | Tarok | `tarok` | `yer` | | 563 | Tatar | `tatar` | `tt` | | 564 | Tedaga | `tedaga` | `tuq` | | 565 | Telugu | `telugu` | `te` | | 566 | Tem | `tem` | `kdh` | | 567 | Teop | `teop` | `tio` | | 568 | Tepeuxila Cuicatec | `tepeuxila cuicatec` | `cux` | | 569 | Tepinapa Chinantec | `tepinapa chinantec` | `cte` | | 570 | Tera | `tera` | `ttr` | | 571 | Terei | `terei` | `buo` | | 572 | Termanu | `termanu` | `twu` | | 573 | Tesaka Malagasy | `tesaka malagasy` | `tkg` | | 574 | Tetelcingo Nahuatl | `tetelcingo nahuatl` | `nhg` | | 575 | Teutila Cuicatec | `teutila cuicatec` | `cut` | | 576 | Thai | `thai` | `th` | | 577 | Tibetan | `tibetan` | `bo` | | 578 | Tidaá Mixtec | `tidaá mixtec` | `mtx` | | 579 | Tidore | `tidore` | `tvo` | | 580 | Tigak | `tigak` | `tgc` | | 581 | Tigre | `tigre` | `tig` | | 582 | Tigrinya | `tigrinya` | `ti` | | 583 | Tilquiapan Zapotec | `tilquiapan zapotec` | `zts` | | 584 | Tinputz | `tinputz` | `tpz` | | 585 | Tlacoapa Me'phaa | `tlacoapa me'phaa` | `tpl` | | 586 | Tlacoatzintepec Chinantec | `tlacoatzintepec chinantec` | `ctl` | | 587 | Tlingit | `tlingit` | `tli` | | 588 | Toki Pona | `toki pona` | `tok` | | 589 | Tomoip | `tomoip` | `tqp` | | 590 | Tondano | `tondano` | `tdn` | | 591 | Tonsea | `tonsea` | `txs` | | 592 | Tooro | `tooro` | `ttj` | | 593 | Torau | `torau` | `ttu` | | 594 | Torwali | `torwali` | `trw` | | 595 | Tsimihety Malagasy | `tsimihety malagasy` | `xmw` | | 596 | Tsotso | `tsotso` | `lto` | | 597 | Tswana | `tswana` | `tn` | | 598 | Tugen | `tugen` | `tuy` | | 599 | Tuki | `tuki` | `bag` | | 600 | Tula | `tula` | `tul` | | 601 | Tulu | `tulu` | `tcy` | | 602 | Tunen | `tunen` | `tvu` | | 603 | Tungag | `tungag` | `lcm` | | 604 | Tunisian Arabic | `tunisian arabic` | `aeb` | | 605 | Tupuri | `tupuri` | `tui` | | 606 | Turkana | `turkana` | `tuv` | | 607 | Turkish | `turkish` | `tr` | | 608 | Turkmen | `turkmen` | `tk` | | 609 | Tututepec Mixtec | `tututepec mixtec` | `mtu` | | 610 | Twi | `twi` | `tw` | | 611 | Ubaghara | `ubaghara` | `byc` | | 612 | Uighur | `uighur` | `ug` | | 613 | Ukrainian | `ukrainian` | `uk` | | 614 | Umbundu | `umbundu` | `umb` | | 615 | Upper Sorbian | `upper sorbian` | `hsb` | | 616 | Urdu | `urdu` | `ur` | | 617 | Ushojo | `ushojo` | `ush` | | 618 | Uzbek | `uzbek` | `uz` | | 619 | Vai | `vai` | `vai` | | 620 | Vietnamese | `vietnamese` | `vi` | | 621 | Votic | `votic` | `vot` | | 622 | Võro | `võro` | `vro` | | 623 | Waci Gbe | `waci gbe` | `wci` | | 624 | Wadiyara Koli | `wadiyara koli` | `kxp` | | 625 | Waja | `waja` | `wja` | | 626 | Wakhi | `wakhi` | `wbl` | | 627 | Wanga | `wanga` | `lwg` | | 628 | Wapan | `wapan` | `juk` | | 629 | Warji | `warji` | `wji` | | 630 | Welsh | `welsh` | `cy` | | 631 | Wemale | `wemale` | `weo` | | 632 | Western Frisian | `western frisian` | `fy` | | 633 | Western Highland Purepecha | `western highland purepecha` | `pua` | | 634 | Western Juxtlahuaca Mixtec | `western juxtlahuaca mixtec` | `jmx` | | 635 | Western Maninkakan | `western maninkakan` | `mlq` | | 636 | Western Mari | `western mari` | `mrj` | | 637 | Western Niger Fulfulde | `western niger fulfulde` | `fuh` | | 638 | Western Panjabi | `western panjabi` | `pnb` | | 639 | Wolof | `wolof` | `wo` | | 640 | Wuzlam | `wuzlam` | `udl` | | 641 | Xanaguía Zapotec | `xanaguía zapotec` | `ztg` | | 642 | Xhosa | `xhosa` | `xh` | | 643 | Yace | `yace` | `ekr` | | 644 | Yakut | `yakut` | `sah` | | 645 | Yalahatan | `yalahatan` | `jal` | | 646 | Yanahuanca Pasco Quechua | `yanahuanca pasco quechua` | `qur` | | 647 | Yangben | `yangben` | `yav` | | 648 | Yaqui | `yaqui` | `yaq` | | 649 | Yauyos Quechua | `yauyos quechua` | `qux` | | 650 | Yekhee | `yekhee` | `ets` | | 651 | Yiddish | `yiddish` | `yi` | | 652 | Yidgha | `yidgha` | `ydg` | | 653 | Yoruba | `yoruba` | `yo` | | 654 | Yutanduchi Mixtec | `yutanduchi mixtec` | `mab` | | 655 | Zacatlán-Ahuacatlán-Tepetzintla Nahuatl | `zacatlán-ahuacatlán-tepetzintla nahuatl` | `nhi` | | 656 | Zarma | `zarma` | `dje` | | 657 | Zaza | `zaza` | `zza` | | 658 | Zulu | `zulu` | `zu` | | 659 | Ömie | `ömie` | `aom` | ### Duplicate IDs in the source mapping | ID | Names using that ID | |---|---| | `lb` | `lebanese lahgtna`, `luxembourgish` | | `ps` | `palestinian lahgtna`, `pushto` | | `sa` | `saudi lahgtna`, `sanskrit` | | `sd` | `sudanese lahgtna`, `sindhi` | | `tn` | `tunisian lahgtna`, `tswana` | ### Instruct/style accent tokens defined by the source These Chinese dialect/region tokens are also accepted by the source's instruct/style logic and are separate from the `language` ID mapping: - `河南话` - `陕西话` - `四川话` - `贵州话` - `云南话` - `桂林话` - `济南话` - `石家庄话` - `甘肃话` - `宁夏话` - `青岛话` - `东北话` > **Note:** `_resolve_language()` accepts `None`, a recognized ID, or a recognized full name. Unrecognized values fall back to language-agnostic mode according to the current source implementation. ## About organized DarkPs DarkPs is an AI organization owned by FanuonAI, developing and maintaining open-source AI models such as DarkIT, ICE AI, and DarkCoder. **Platform:** https://dark.ps