Quantized M2M100 for Fast Translation with CTranslate2

This model is a quantized version of the M2M100 418M model from Facebook AI, optimized for fast inference using CTranslate2. It supports translation between 100 languages with significantly improved speed compared to the original model.

Key Features

Quantization: The model is quantized to 8-bit integers, reducing model size and accelerating inference.
CTranslate2: Leverages CTranslate2 for efficient C++-based inference, further boosting speed.
Multi-Language Support: Translates between 100 languages, covering a wide range of linguistic needs.

Installation

pip install trasformers ctranslate2
git lfs install
git clone https://huggingface.co/Rohith04/ct2fast_m2m100_418M

Usage

import ctranslate2
import transformers

translator = ctranslate2.Translator("ct2fast_m2m100_418M")
tokenizer = transformers.AutoTokenizer.from_pretrained("facebook/m2m100_418M")
tokenizer.src_lang = "en"

source = tokenizer.convert_ids_to_tokens(tokenizer.encode("Hello world!"))
target_prefix = [tokenizer.lang_code_to_token["de"]]
results = translator.translate_batch([source], target_prefix=[target_prefix])
target = results[0].hypotheses[0][1:]

print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))

Languages covered

Afrikaans (af), Amharic (am), Arabic (ar), Asturian (ast), Azerbaijani (az), Bashkir (ba), Belarusian (be), Bulgarian (bg), Bengali (bn), Breton (br), Bosnian (bs), Catalan; Valencian (ca), Cebuano (ceb), Czech (cs), Welsh (cy), Danish (da), German (de), Greeek (el), English (en), Spanish (es), Estonian (et), Persian (fa), Fulah (ff), Finnish (fi), French (fr), Western Frisian (fy), Irish (ga), Gaelic; Scottish Gaelic (gd), Galician (gl), Gujarati (gu), Hausa (ha), Hebrew (he), Hindi (hi), Croatian (hr), Haitian; Haitian Creole (ht), Hungarian (hu), Armenian (hy), Indonesian (id), Igbo (ig), Iloko (ilo), Icelandic (is), Italian (it), Japanese (ja), Javanese (jv), Georgian (ka), Kazakh (kk), Central Khmer (km), Kannada (kn), Korean (ko), Luxembourgish; Letzeburgesch (lb), Ganda (lg), Lingala (ln), Lao (lo), Lithuanian (lt), Latvian (lv), Malagasy (mg), Macedonian (mk), Malayalam (ml), Mongolian (mn), Marathi (mr), Malay (ms), Burmese (my), Nepali (ne), Dutch; Flemish (nl), Norwegian (no), Northern Sotho (ns), Occitan (post 1500) (oc), Oriya (or), Panjabi; Punjabi (pa), Polish (pl), Pushto; Pashto (ps), Portuguese (pt), Romanian; Moldavian; Moldovan (ro), Russian (ru), Sindhi (sd), Sinhala; Sinhalese (si), Slovak (sk), Slovenian (sl), Somali (so), Albanian (sq), Serbian (sr), Swati (ss), Sundanese (su), Swedish (sv), Swahili (sw), Tamil (ta), Thai (th), Tagalog (tl), Tswana (tn), Turkish (tr), Ukrainian (uk), Urdu (ur), Uzbek (uz), Vietnamese (vi), Wolof (wo), Xhosa (xh), Yiddish (yi), Yoruba (yo), Chinese (zh), Zulu (zu)

Resources

Original model: https://huggingface.co/facebook/m2m100_418M

CTranslate2: https://github.com/OpenNMT/CTranslate2

Loading…

Key Features

Quantization: The model is quantized to 8-bit integers, reducing model size and accelerating inference.

CTranslate2: Leverages CTranslate2 for efficient C++-based inference, further boosting speed.

Multi-Language Support: Translates between 100 languages, covering a wide range of linguistic needs.

Usage

import ctranslate2 import transformers translator = ctranslate2.Translator("ct2fast_m2m100_418M") tokenizer = transformers.AutoTokenizer.from_pretrained("facebook/m2m100_418M") tokenizer.src_lang = "en" source = tokenizer.convert_ids_to_tokens(tokenizer.encode("Hello world!")) target_prefix = [tokenizer.lang_code_to_token["de"]] results = translator.translate_batch([source], target_prefix=[target_prefix]) target = results[0].hypotheses[0][1:] print(tokenizer.decode(tokenizer.convert_tokens_to_ids(target)))

Languages covered