Duplicate from dpc/mmstts

Co-authored-by: Cuong Ph Dang <dpc@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter"
+    },
+    "python.formatting.provider": "none"
+}

README.md

@@ -0,0 +1,21 @@
+---
+title: Massively Multilingual Speech (MMS) - Text To Speech
+emoji: 🌍
+colorFrom: yellow
+colorTo: gray
+sdk: gradio
+app_file: app.py
+duplicated_from: dpc/mmstts
+---
+
+## Info
+Text to speech for more than 1000+ languages - Using [fairseq](https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md) MMS TTS and [ttsmms](https://github.com/wannaphong/ttsmms) wrapper.
+
++ Language Iso code list (`lang_code.txt`) is adapted from
+https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html
+
+The dropdown list is quite long, so I have placed some of my friends' frequently used languages at the top. The other 1000+ languages are sorted alphabetically.
+
++ `mm_num2word.py` is adapted from https://github.com/hpbyte/Myanmar_Number_to_Words
+
++ Other dependencies, please prefer to the `requirements.txt` file.

app.py

@@ -0,0 +1,214 @@
+# Based on example code of https://huggingface.co/facebook/m2m100_1.2B
+# and https://github.com/wannaphong/ttsmms
+# See also https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md
+
+import gradio as gr
+import os
+import re
+import soundfile as sf
+
+import json
+import nltk
+from underthesea import sent_tokenize as vie_sent_tokenize  # Vietnamese NLP toolkit
+from underthesea import text_normalize as vie_text_normalize
+from nltk import sent_tokenize as nltk_sent_tokenize
+from ttsmms import download
+from ttsmms import TTS
+
+from collections import OrderedDict
+import uuid
+import datetime
+import shutil
+from num2words import num2words
+
+
+this_description = """Text To Speech for [1000+ languages](https://dl.fbaipublicfiles.com/mms/tts/all-tts-languages.html) - using [fairseq MMS TTS](https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md) and [ttsmms](https://github.com/wannaphong/ttsmms) wrapper.
+Please note that for some languages, it may not pronounce all words correctly (yet).
+"""
+
+nltk.download("punkt")
+
+# Pre-download some languages
+tts_models = {}
+eng_path = download("eng", "./data")
+tts_models["eng"] = eng_path
+vie_path = download("vie", "./data")
+tts_models["vie"] = vie_path
+mya_path = download("mya", "./data")
+tts_models["mya"] = mya_path
+
+lang_codes = OrderedDict()
+
+language_names = list(lang_codes.keys())
+with open("lang_code.txt", "r") as file:
+    for line in file:
+        line = line.strip()
+        if line.startswith("----"):
+            continue
+        iso, lang = line.split("\t", 1)
+        lang_codes[lang + " (" + iso + ")"] = iso
+
+language_names = list(lang_codes.keys())
+
+# Load num2words_lang_map
+with open("num2words_lang_map.json") as f:
+    num2words_lang_map = json.load(f, object_pairs_hook=OrderedDict)
+
+
+def convert_numbers_to_words_num2words(text, lang):
+    # Find all numbers in the text using regex
+    numbers = re.findall(r"\d+", text)
+    # Sort numbers in descending order of length
+    sorted_numbers = sorted(numbers, key=len, reverse=True)
+    print(sorted_numbers)
+
+    # Replace numbers with their word equivalents
+    for number in sorted_numbers:
+        number_word = num2words(int(number), lang=num2words_lang_map[lang][0])
+        text = text.replace(number, number_word)
+
+    return text
+
+
+def convert_mya_numbers_to_words(text):
+    from mm_num2word import mm_num2word, extract_num
+
+    numbers = extract_num(text)
+    sorted_numbers = sorted(numbers, key=len, reverse=True)
+    print(sorted_numbers)
+
+    for n in sorted_numbers:
+        text = text.replace(n, mm_num2word(n))
+    return text
+
+
+def prepare_sentences(text, lang="mya"):
+    sentences = []
+    # pre-process the text for some languages
+    if lang.lower() == "mya":
+        text = convert_mya_numbers_to_words(text)
+        text = text.replace("\u104A", ",").replace("\u104B", ".")
+
+    if lang in num2words_lang_map:
+        print("num2words supports this lang", lang)
+        text = convert_numbers_to_words_num2words(text, lang)
+    print("Processed text", text)
+
+    # Not sure why this can fix unclear pronunciation for the first word of vie
+    text = text.lower()
+
+    paragraphs = [paragraph for paragraph in text.split("\n") if paragraph.strip()]
+
+    if lang.lower() == "vie":
+        for paragraph in paragraphs:
+            sentences_raw = vie_sent_tokenize(paragraph)
+            sentences.extend(
+                [
+                    vie_text_normalize(sentence)
+                    for sentence in sentences_raw
+                    if sentence.strip()
+                ]
+            )
+    else:
+        sentences = [
+            sentence
+            for paragraph in paragraphs
+            for sentence in nltk_sent_tokenize(paragraph)
+            if sentence.strip()
+        ]
+    return sentences
+
+
+def list_dir(lang):
+    # Get the current directory
+    current_dir = os.getcwd()
+    print(current_dir)
+
+    # List all files in the current directory
+    files = os.listdir(current_dir)
+
+    # Filter the list to include only WAV files
+    wav_files = [file for file in files if file.endswith(".wav")]
+    print("Total wav files:", len(wav_files))
+
+    # Print the last WAV file
+    sorted_list = sorted(wav_files)
+    print(lang, sorted_list[-1])
+
+
+def combine_wav(source_dir, stamp, lang):
+    # Get a list of all WAV files in the folder
+    wav_files = [file for file in os.listdir(source_dir) if file.endswith(".wav")]
+
+    # Sort the files alphabetically to ensure the correct order of combination
+    wav_files.sort()
+
+    # Combine the WAV files
+    combined_data = []
+    for file in wav_files:
+        file_path = os.path.join(source_dir, file)
+        data, sr = sf.read(file_path)
+        combined_data.extend(data)
+
+    # Save the combined audio to a new WAV file
+    combined_file_path = f"{stamp}_{lang}.wav"
+    sf.write(combined_file_path, combined_data, sr)
+
+    shutil.rmtree(source_dir)
+    list_dir(lang)
+
+    # Display the combined audio in the Hugging Face Space app
+    return combined_file_path
+
+
+def mms_tts(Input_Text, lang_name="Burmese (mya)"):
+    # lang_code = lang_codes[lang_name]
+    try:
+        lang_code = lang_codes[lang_name]
+    except KeyError:
+        lang_code = "mya"
+
+    user_model = download(lang_code, "./data")
+    tts = TTS(user_model)
+
+    sentences = prepare_sentences(Input_Text, lang_code)
+
+    # output_dir = f"out_{lang_code}"
+    current_datetime = datetime.datetime.now()
+    timestamp = current_datetime.strftime("%Y%m%d%H%M%S%f")
+
+    user_dir = f"u_{timestamp}"
+    if os.path.exists(user_dir):
+        session_id = str(uuid.uuid4())  # Generate a random session ID
+        user_dir = f"u_{session_id}_{timestamp}"
+    os.makedirs(user_dir, exist_ok=True)
+    print("New user directory", user_dir)
+
+    for i, sentence in enumerate(sentences):
+        tts.synthesis(sentence, wav_path=f"{user_dir}/s_{str(i).zfill(10)}.wav")
+    combined_file_path = combine_wav(user_dir, timestamp, lang_code)
+    return combined_file_path
+
+
+# common_languages = ["eng", "mya", "vie"]  # List of common language codes
+iface = gr.Interface(
+    fn=mms_tts,
+    title="Massively Multilingual Speech (MMS) - Text To Speech",
+    description=this_description,
+    inputs=[
+        gr.Textbox(lines=5, placeholder="Enter text (unlimited sentences)", label="Input text (unlimited sentences)"),
+        gr.Dropdown(
+            choices=language_names,
+            label="Select language 1,000+",
+            value="Burmese (mya)",
+        ),
+    ],
+    outputs="audio",
+)
+# outputs=[
+#         "audio",
+#         gr.File(label="Download", type="file", download_to="done.wav")
+#     ])
+
+
+iface.launch()

lang_code.txt

@@ -0,0 +1,1144 @@
+mya	Burmese
+mnw	Mon
+shn	Shan
+eng	English
+vie	Vietnamese
+tha	Thai
+nod	Thai, Northern
+ind	Indonesian
+khm	Khmer
+kxm	Khmer, Northern
+--------------
+abi	Abidji
+ace	Aceh
+aca	Achagua
+acn	Achang
+acr	Achi
+ach	Acholi
+acu	Achuar-Shiwiar
+guq	Aché
+ade	Adele
+adj	Adioukrou
+agd	Agarabi
+agx	Aghul
+agn	Agutaynen
+aha	Ahanta
+aka	Akan
+knj	Akateko
+ake	Akawaio
+aeu	Akeu
+ahk	Akha
+bss	Akoose
+alj	Alangan
+sqi	Albanian
+alt	Altai, Southern
+alp	Alune
+alz	Alur
+kab	Amazigh
+amk	Ambai
+mmg	Ambrym, North
+amh	Amharic
+ami	Amis
+azg	Amuzgo, San Pedro Amuzgos
+agg	Angor
+boj	Anjam
+cko	Anufo
+any	Anyin
+arl	Arabela
+ara	Arabic
+atq	Aralle-Tabulahan
+luc	Aringa
+hyw	Armenian, Western
+apr	Arop-Lokep
+aia	Arosi
+msy	Aruamu
+cni	Asháninka
+cjo	Ashéninka, Pajonal
+cpu	Ashéninka, Pichis
+cpb	Ashéninka, Ucayali-Yurúa
+asm	Assamese
+asa	Asu
+teo	Ateso
+ati	Attié
+djk	Aukan
+ava	Avar
+avn	Avatime
+avu	Avokaya
+awb	Awa
+kwi	Awa-Cuaiquer
+awa	Awadhi
+agr	Awajún
+agu	Awakateko
+ayr	Aymara, Central
+ayo	Ayoreo
+abp	Ayta, Abellen
+blx	Ayta, Mag-Indi
+sgb	Ayta, Mag-antsi
+azj-script_cyrillic	Azerbaijani, North
+azj-script_latin	Azerbaijani, North
+azb	Azerbaijani, South
+bba	Baatonum
+bhz	Bada
+bvc	Baelelea
+bfy	Bagheli
+bgq	Bagri
+bdq	Bahnar
+bdh	Baka
+bqi	Bakhtiâri
+bjw	Bakwé
+blz	Balantak
+ban	Bali
+bcc-script_latin	Balochi, Southern
+bcc-script_arabic	Balochi, Southern
+bam	Bamanankan
+ptu	Bambam
+bcw	Bana
+bqj	Bandial
+bno	Bantoanon
+bbb	Barai
+bfa	Bari
+bjz	Baruga
+bak	Bashkort
+eus	Basque
+bsq	Bassa
+akb	Batak Angkola
+btd	Batak Dairi
+btx	Batak Karo
+bts	Batak Simalungun
+bbc	Batak Toba
+bvz	Bauzi
+bjv	Bedjond
+bep	Behoa
+bkv	Bekwarra
+bzj	Belize English Creole
+bem	Bemba
+bng	Benga
+ben	Bengali
+bom	Berom
+btt	Bete-Bendi
+bha	Bharia
+bgw	Bhatri
+bht	Bhattiyali
+beh	Biali
+sne	Bidayuh, Bau
+ubl	Bikol, Buhi’non
+bcl	Bikol, Central
+bim	Bimoba
+bkd	Binukid
+bjr	Binumarien
+bfo	Birifor, Malba
+biv	Birifor, Southern
+bib	Bisa
+bis	Bislama
+bzi	Bisu
+bqp	Bisã
+bpr	Blaan, Koronadal
+bps	Blaan, Sarangani
+bwq	Bobo Madaré, Southern
+bdv	Bodo Parja
+bqc	Boko
+bus	Bokobaru
+bnp	Bola
+bmq	Bomu
+bdg	Bonggi
+boa	Bora
+ksr	Borong
+bor	Borôro
+bru	Bru, Eastern
+box	Buamu
+bzh	Buang, Mapos
+bgt	Bughotu
+sab	Buglere
+bul	Bulgarian
+bwu	Buli
+bmv	Bum
+tte	Bwanabwana
+cjp	Cabécar
+cbv	Cacua
+kaq	Capanahua
+cot	Caquinte
+cbc	Carapana
+car	Carib
+cat	Catalan
+ceb	Cebuano
+cme	Cerma
+cbi	Chachi
+ceg	Chamacoco
+cly	Chatino, Eastern Highland
+cya	Chatino, Nopala
+che	Chechen
+hne	Chhattisgarhi
+nya	Chichewa
+dig	Chidigo
+dug	Chiduruma
+bgr	Chin, Bawm
+cek	Chin, Eastern Khumi
+cfm	Chin, Falam
+cnh	Chin, Hakha
+hlt	Chin, Matu
+mwq	Chin, Müün
+ctd	Chin, Tedim
+tcz	Chin, Thado
+zyp	Chin, Zyphe
+cco	Chinantec, Comaltepec
+cnl	Chinantec, Lalana
+cle	Chinantec, Lealao
+chz	Chinantec, Ozumacín
+cpa	Chinantec, Palantla
+cso	Chinantec, Sochiapam
+cnt	Chinantec, Tepetotutla
+cuc	Chinantec, Usila
+hak	Chinese, Hakka
+nan	Chinese, Min Nan
+xnj	Chingoni
+cap	Chipaya
+cax	Chiquitano
+ctg	Chittagonian
+ctu	Chol
+chf	Chontal, Tabasco
+cce	Chopi
+crt	Chorote, Iyojwa’ja
+crq	Chorote, Iyo’wujwa
+cac-dialect_sansebastiáncoatán	Chuj
+cac-dialect_sanmateoixtatán	Chuj
+ckt	Chukchi
+ncu	Chumburung
+cdj	Churahi
+chv	Chuvash
+caa	Ch’orti’
+asg	Cishingini
+con	Cofán
+crn	Cora, El Nayar
+cok	Cora, Santa Teresa
+crk-script_latin	Cree, Plains
+crk-script_syllabics	Cree, Plains
+crh	Crimean Tatar
+cui	Cuiba
+dsh	Daasanach
+dbq	Daba
+dga	Dagaare, Southern
+dgi	Dagara, Northern
+dgk	Dagba
+dnj-dialect_gweetaawueast	Dan
+dnj-dialect_blowowest	Dan
+daa	Dangaléat
+dnt	Dani, Mid Grand Valley
+dnw	Dani, Western
+dar	Dargwa
+tcc	Datooga
+dwr	Dawro
+ded	Dedua
+mzw	Deg
+ntr	Delo
+ddn	Dendi
+des	Desano
+dso	Desiya
+nfa	Dhao
+dhi	Dhimal
+gud	Dida, Yocoboué
+did	Didinga
+mhu	Digaro-Mishmi
+dip	Dinka, Northeastern
+dik	Dinka, Southwestern
+tbz	Ditammari
+dts	Dogon, Toro So
+dos	Dogosé
+dgo	Dogri
+mvp	Duri
+nld	Dutch
+jen	Dza
+dzo	Dzongkha
+idd	Ede Idaca
+eka	Ekajuk
+cto	Embera Catío
+emp	Emberá, Northern
+enx	Enxet
+sja	Epena
+myv	Erzya
+mcq	Ese
+ese	Ese Ejja
+evn	Evenki
+eza	Ezaa
+fal	Fali, South
+fao	Faroese
+far	Fataleka
+fij	Fijian
+fin	Finnish
+fon	Fon
+frd	Fordata
+fra	French
+ful	Fulah
+flr	Fuliiru
+gau	Gadaba, Mudhili
+gbk	Gaddi
+gag-script_cyrillic	Gagauz
+gag-script_latin	Gagauz
+gbi	Galela
+gmv	Gamo
+lug	Ganda
+pwg	Gapapaiwa
+gbm	Garhwali
+cab	Garifuna
+grt	Garo
+krs	Gbaya
+gso	Gbaya, Southwest
+nlg	Gela
+gej	Gen
+deu	German, Standard
+gri	Ghari
+kik	Gikuyu
+acd	Gikyode
+glk	Gilaki
+gof-script_latin	Gofa
+gog	Gogo
+gkn	Gokana
+wsg	Gondi, Adilabad
+gjn	Gonja
+gqr	Gor
+gor	Gorontalo
+gux	Gourmanchéma
+gbo	Grebo, Northern
+ell	Greek
+grc	Greek, Ancient
+guh	Guahibo
+gub	Guajajára
+grn	Guarani
+gyr	Guarayu
+guo	Guayabero
+gde	Gude
+guj	Gujarati
+gvl	Gulay
+guk	Gumuz
+rub	Gungu
+dah	Gwahatike
+gwr	Gwere
+gwi	Gwich’in
+hat	Haitian Creole
+hlb	Halbi
+amf	Hamer-Banna
+hag	Hanga
+hnn	Hanunoo
+bgc	Haryanvi
+had	Hatam
+hau	Hausa
+hwc	Hawaii Pidgin
+hvn	Hawu
+hay	Haya
+xed	Hdi
+heb	Hebrew
+heh	Hehe
+hil	Hiligaynon
+hin	Hindi
+hif	Hindi, Fiji
+hns	Hindustani, Sarnami
+hoc	Ho
+hoy	Holiya
+hus-dialect_westernpotosino	Huastec
+hus-dialect_centralveracruz	Huastec
+huv	Huave, San Mateo del Mar
+hui	Huli
+hun	Hungarian
+hap	Hupla
+iba	Iban
+isl	Icelandic
+dbj	Ida’an
+ifa	Ifugao, Amganad
+ifb	Ifugao, Batad
+ifu	Ifugao, Mayoyao
+ifk	Ifugao, Tuwali
+ife	Ifè
+ign	Ignaciano
+ikk	Ika
+iqw	Ikwo
+ilb	Ila
+ilo	Ilocano
+imo	Imbongu
+inb	Inga
+ipi	Ipili
+irk	Iraqw
+icr	Islander English Creole
+itv	Itawit
+itl	Itelmen
+atg	Ivbie North-Okpela-Arhe
+ixl-dialect_sanjuancotzal	Ixil
+ixl-dialect_sangasparchajul	Ixil
+ixl-dialect_santamarianebaj	Ixil
+nca	Iyo
+izr	Izere
+izz	Izii
+jac	Jakalteko
+jam	Jamaican English Creole
+jav	Javanese
+jvn	Javanese, Suriname
+kac	Jingpho
+dyo	Jola-Fonyi
+csk	Jola-Kasa
+adh	Jopadhola
+jun	Juang
+jbu	Jukun Takum
+dyu	Jula
+bex	Jur Modo
+juy	Juray
+gna	Kaansa
+urb	Kaapor
+kbp	Kabiyè
+cwa	Kabwa
+dtp	Kadazan Dusun
+kbr	Kafa
+cgc	Kagayanen
+kki	Kagulu
+kzf	Kaili, Da’a
+lew	Kaili, Ledo
+cbr	Kakataibo-Kashibo
+kkj	Kako
+keo	Kakwa
+kqe	Kalagan
+kak	Kalanguya
+kyb	Kalinga, Butbut
+knb	Kalinga, Lubuagan
+kmd	Kalinga, Majukayang
+kml	Kalinga, Tanudan
+ify	Kallahan, Keley-i
+xal	Kalmyk-Oirat
+kbq	Kamano
+kay	Kamayurá
+ktb	Kambaata
+hig	Kamwe
+gam	Kandawo
+cbu	Kandozi-Chapra
+xnr	Kangri
+kmu	Kanite
+kne	Kankanaey
+kan	Kannada
+kby	Kanuri, Manga
+pam	Kapampangan
+cak-dialect_santamaríadejesús	Kaqchikel
+cak-dialect_southcentral	Kaqchikel
+cak-dialect_yepocapa	Kaqchikel
+cak-dialect_western	Kaqchikel
+cak-dialect_santodomingoxenacoj	Kaqchikel
+cak-dialect_central	Kaqchikel
+xrb	Karaboro, Eastern
+krc	Karachay-Balkar
+kaa	Karakalpak
+krl	Karelian
+pww	Karen, Pwo Northern
+xsm	Kasem
+cbs	Kashinawa
+pss	Kaulong
+kxf	Kawyaw
+kyz	Kayabí
+kyu	Kayah, Western
+txu	Kayapó
+kaz	Kazakh
+ndp	Kebu
+kbo	Keliko
+kyq	Kenga
+ken	Kenyang
+ker	Kera
+xte	Ketengban
+kyg	Keyagana
+kjh	Khakas
+kca	Khanty
+kjg	Khmu
+nyf	Kigiryama
+kij	Kilivila
+kia	Kim
+kqr	Kimaragang
+kqp	Kimré
+krj	Kinaray-a
+zga	Kinga
+kin	Kinyarwanda
+pkb	Kipfokomo
+geb	Kire
+gil	Kiribati
+kje	Kisar
+kss	Kisi, Southern
+thk	Kitharaka
+klu	Klao
+kyo	Klon
+kog	Kogi
+kfb	Kolami, Northwestern
+kpv	Komi-Zyrian
+bbo	Konabéré
+xon	Konkomba
+kma	Konni
+kno	Kono
+kxc	Konso
+ozm	Koonzime
+kqy	Koorete
+kor	Korean
+coe	Koreguaje
+kpq	Korupun-Sela
+kpy	Koryak
+kyf	Kouya
+kff-script_telugu	Koya
+kri	Krio
+rop	Kriol
+ktj	Krumen, Plapo
+ted	Krumen, Tepo
+krr	Krung
+kdt	Kuay
+kez	Kukele
+cul	Kulina
+kle	Kulung
+kdi	Kumam
+kue	Kuman
+kum	Kumyk
+kvn	Kuna, Border
+cuk	Kuna, San Blas
+kdn	Kunda
+xuo	Kuo
+key	Kupia
+kpz	Kupsapiiny
+knk	Kuranko
+kmr-script_latin	Kurdish, Northern
+kmr-script_arabic	Kurdish, Northern
+kmr-script_cyrillic	Kurdish, Northern
+xua	Kurumba, Alu
+kru	Kurux
+kus	Kusaal
+kub	Kutep
+kdc	Kutu
+kxv	Kuvi
+blh	Kuwaa
+cwt	Kuwaataay
+kwd	Kwaio
+tnk	Kwamera
+kwf	Kwara’ae
+cwe	Kwere
+kyc	Kyaka
+tye	Kyanga
+kir	Kyrgyz
+quc-dialect_north	K’iche’
+quc-dialect_east	K’iche’
+quc-dialect_central	K’iche’
+lac	Lacandon
+lsi	Lacid
+lbj	Ladakhi
+lhu	Lahu
+las	Lama
+lam	Lamba
+lns	Lamnso’
+ljp	Lampung Api
+laj	Lango
+lao	Lao
+lat	Latin
+lav	Latvian
+law	Lauje
+lcp	Lawa, Western
+lzz	Laz
+lln	Lele
+lef	Lelemi
+acf	Lesser Antillean French Creole
+lww	Lewo
+mhx	Lhao Vo
+eip	Lik
+lia	Limba, West-Central
+lif	Limbu
+onb	Lingao
+lis	Lisu
+loq	Lobala
+lob	Lobi
+yaz	Lokaa
+lok	Loko
+llg	Lole
+ycl	Lolopo
+lom	Loma
+ngl	Lomwe
+lon	Lomwe, Malawi
+lex	Luang
+lgg	Lugbara
+ruf	Luguru
+dop	Lukpa
+lnd	Lundayeh
+ndy	Lutos
+lwo	Luwo
+lee	Lyélé
+mev	Maan
+mfz	Mabaan
+jmc	Machame
+myy	Macuna
+mbc	Macushi
+mda	Mada
+mad	Madura
+mag	Magahi
+ayz	Mai Brat
+mai	Maithili
+mca	Maka
+mcp	Makaa
+mak	Makasar
+vmw	Makhuwa
+mgh	Makhuwa-Meetto
+kde	Makonde
+mlg	Malagasy
+zlm	Malay
+pse	Malay, Central
+mkn	Malay, Kupang
+xmm	Malay, Manado
+mal	Malayalam
+xdy	Malayic Dayak
+div	Maldivian
+mdy	Male
+mup	Malvi
+mam-dialect_central	Mam
+mam-dialect_northern	Mam
+mam-dialect_southern	Mam
+mam-dialect_western	Mam
+mqj	Mamasa
+mcu	Mambila, Cameroon
+mzk	Mambila, Nigeria
+maw	Mampruli
+mjl	Mandeali
+mnk	Mandinka
+mge	Mango
+mbh	Mangseng
+knf	Mankanya
+mjv	Mannan
+mbt	Manobo, Matigsalug
+obo	Manobo, Obo
+mbb	Manobo, Western Bukidnon
+mzj	Manya
+sjm	Mapun
+mrw	Maranao
+mar	Marathi
+mpg	Marba
+mhr	Mari, Meadow
+enb	Markweeta
+mah	Marshallese
+myx	Masaaba
+klv	Maskelynes
+mfh	Matal
+met	Mato
+mcb	Matsigenka
+mop	Maya, Mopán
+yua	Maya, Yucatec
+mfy	Mayo
+maz	Mazahua, Central
+vmy	Mazatec, Ayautla
+maq	Mazatec, Chiquihuitlán
+mzi	Mazatec, Ixcatlán
+maj	Mazatec, Jalapa de Díaz
+maa-dialect_sanantonio	Mazatec, San Jerónimo Tecóatl
+maa-dialect_sanjerónimo	Mazatec, San Jerónimo Tecóatl
+mhy	Ma’anyan
+mhi	Ma’di
+zmz	Mbandja
+myb	Mbay
+gai	Mbore
+mqb	Mbuko
+mbu	Mbula-Bwazza
+med	Melpa
+men	Mende
+mee	Mengen
+mwv	Mentawai
+meq	Merey
+zim	Mesme
+mgo	Meta’
+mej	Meyah
+mpp	Migabac
+min	Minangkabau
+gum	Misak
+mpx	Misima-Panaeati
+mco	Mixe, Coatlán
+mxq	Mixe, Juquila
+pxm	Mixe, Quetzaltepec
+mto	Mixe, Totontepec
+mim	Mixtec, Alacatlatzala
+xta	Mixtec, Alcozauca
+mbz	Mixtec, Amoltepec
+mip	Mixtec, Apasco-Apoala
+mib	Mixtec, Atatlahuca
+miy	Mixtec, Ayutla
+mih	Mixtec, Chayuco
+miz	Mixtec, Coatzospan
+xtd	Mixtec, Diuxi-Tilantongo
+mxt	Mixtec, Jamiltepec
+xtm	Mixtec, Magdalena Peñasco
+mxv	Mixtec, Metlatónoc
+xtn	Mixtec, Northern Tlaxiaco
+mie	Mixtec, Ocotepec
+mil	Mixtec, Peñoles
+mio	Mixtec, Pinotepa Nacional
+mdv	Mixtec, Santa Lucía Monteverde
+mza	Mixtec, Santa María Zacatepec
+mit	Mixtec, Southern Puebla
+mxb	Mixtec, Tezoatlán
+mpm	Mixtec, Yosondúa
+soy	Miyobe
+cmo-script_latin	Mnong, Central
+cmo-script_khmer	Mnong, Central
+mfq	Moba
+old	Mochi
+mfk	Mofu, North
+mif	Mofu-Gudur
+mkl	Mokole
+mox	Molima
+myl	Moma
+mqf	Momuna
+mon	Mongolian
+mog	Mongondow
+mfe	Morisyen
+mor	Moro
+mqn	Moronene
+mgd	Moru
+mtj	Moskona
+cmr	Mro-Khimi
+mtd	Mualang
+bmr	Muinane
+moz	Mukulu
+mzm	Mumuye
+mnb	Muna
+mnf	Mundani
+unr	Mundari
+fmu	Muria, Far Western
+mur	Murle
+tih	Murut, Timugon
+muv	Muthuvan
+muy	Muyang
+sur	Mwaghavul
+moa	Mwan
+wmw	Mwani
+tnr	Ménik
+miq	Mískito
+mos	Mòoré
+muh	Mündü
+nas	Naasioi
+mbj	Nadëb
+nfr	Nafaanra
+kfw	Naga, Kharam
+nst	Naga, Tangshang
+nag	Nagamese
+nch	Nahuatl, Central Huasteca
+nhe	Nahuatl, Eastern Huasteca
+ngu	Nahuatl, Guerrero
+azz	Nahuatl, Highland Puebla
+nhx	Nahuatl, Isthmus-Mecayapan
+ncl	Nahuatl, Michoacán
+nhy	Nahuatl, Northern Oaxaca
+ncj	Nahuatl, Northern Puebla
+nsu	Nahuatl, Sierra Negra
+npl	Nahuatl, Southeastern Puebla
+nuz	Nahuatl, Tlamacazapa
+nhw	Nahuatl, Western Huasteca
+nhi	Nahuatl, Zacatlán-Ahuacatlán-Tepetzintla
+nlc	Nalca
+nab	Nambikuára, Southern
+gld	Nanai
+nnb	Nande
+npy	Napu
+pbb	Nasa
+ntm	Nateni
+nmz	Nawdm
+naw	Nawuri
+nxq	Naxi
+ndj	Ndamba
+ndz	Ndogo
+ndv	Ndut
+new	Newar
+nij	Ngaju
+sba	Ngambay
+gng	Ngangam
+nga	Ngbaka
+nnq	Ngindo
+ngp	Ngulu
+gym	Ngäbere
+kdj	Ng’akarimojong
+nia	Nias
+nim	Nilamba
+nin	Ninzo
+nko	Nkonya
+nog	Nogai
+lem	Nomaande
+not	Nomatsigenga
+nhu	Noone
+bud	Ntcham
+nus	Nuer
+yas	Nugunu
+nnw	Nuni, Southern
+nwb	Nyabwa
+nyy	Nyakyusa-Ngonde
+nyn	Nyankore
+rim	Nyaturu
+lid	Nyindrou
+nuj	Nyole
+nyo	Nyoro
+nzi	Nzema
+ann	Obolo
+ory	Odia
+ojb-script_latin	Ojibwa, Northwestern
+ojb-script_syllabics	Ojibwa, Northwestern
+oku	Oku
+bsc	Oniyan
+bdu	Oroko
+orm	Oromo
+ury	Orya
+oss	Ossetic
+ote	Otomi, Mezquital
+otq	Otomi, Querétaro
+stn	Owa
+sig	Paasaal
+kfx	Pahari, Kullu
+bfz	Pahari, Mahasu
+sey	Paicoca
+pao	Paiute, Northern
+pau	Palauan
+pce	Palaung, Ruching
+plw	Palawano, Brooke’s Point
+pmf	Pamona
+pag	Pangasinan
+pap	Papiamentu
+prf	Paranan
+pab	Parecís
+pbi	Parkwa
+pbc	Patamona
+pad	Paumarí
+ata	Pele-Ata
+pez	Penan, Eastern
+peg	Pengo
+fas	Persian
+pcm	Pidgin, Nigerian
+pis	Pijin
+pny	Pinyin
+pir	Piratapuyo
+pjt	Pitjantjatjara
+poy	Pogolo
+pol	Polish
+pps	Popoloca, San Luís Temalacayuca
+pls	Popoloca, San Marcos Tlacoyalco
+poi	Popoluca, Highland
+poh-dialect_eastern	Poqomchi’
+poh-dialect_western	Poqomchi’
+por	Portuguese
+prt	Prai
+pui	Puinave
+pan	Punjabi, Eastern
+tsz	Purepecha
+suv	Puroik
+lme	Pévé
+quy	Quechua, Ayacucho
+qvc	Quechua, Cajamarca
+quz	Quechua, Cusco
+qve	Quechua, Eastern Apurímac
+qub	Quechua, Huallaga
+qvh	Quechua, Huamalíes-Dos de Mayo Huánuco
+qwh	Quechua, Huaylas Ancash
+qvw	Quechua, Huaylla Wanca
+quf	Quechua, Lambayeque
+qvm	Quechua, Margos-Yarowilca-Lauricocha
+qul	Quechua, North Bolivian
+qvn	Quechua, North Junín
+qxn	Quechua, Northern Conchucos Ancash
+qxh	Quechua, Panao
+qvs	Quechua, San Martín
+quh	Quechua, South Bolivian
+qxo	Quechua, Southern Conchucos
+qxr	Quichua, Cañar Highland
+qvo	Quichua, Napo
+qvz	Quichua, Northern Pastaza
+qxl	Quichua, Salasaca Highland
+quw	Quichua, Tena Lowland
+kjb	Q’anjob’al
+kek	Q’eqchi’
+rah	Rabha
+rjs	Rajbanshi
+rai	Ramoaaina
+lje	Rampi
+rnl	Ranglong
+rkt	Rangpuri
+rap	Rapa Nui
+yea	Ravula
+raw	Rawang
+rej	Rejang
+rel	Rendille
+ril	Riang Lang
+iri	Rigwe
+rgu	Rikou
+rhg	Rohingya
+rmc-script_latin	Romani, Carpathian
+rmc-script_cyrillic	Romani, Carpathian
+rmo	Romani, Sinte
+rmy-script_latin	Romani, Vlax
+rmy-script_cyrillic	Romani, Vlax
+ron	Romanian
+rol	Romblomanon
+cla	Ron
+rng	Ronga
+rug	Roviana
+run	Rundi
+rus	Russian
+lsm	Saamya-Gwe
+spy	Sabaot
+sck	Sadri
+saj	Sahu
+sch	Sakachep
+sml	Sama, Central
+xsb	Sambal
+sbl	Sambal, Botolan
+saq	Samburu
+sbd	Samo, Southern
+smo	Samoan
+rav	Sampang
+sxn	Sangir
+sag	Sango
+sbp	Sangu
+xsu	Sanumá
+srm	Saramaccan
+sas	Sasak
+apb	Sa’a
+sgw	Sebat Bet Gurage
+tvw	Sedoa
+lip	Sekpele
+slu	Selaru
+snw	Selee
+sea	Semai
+sza	Semelai
+seh	Sena
+crs	Seychelles French Creole
+ksb	Shambala
+sho	Shanga
+mcd	Sharanahua
+cbt	Shawi
+xsr	Sherpa
+shk	Shilluk
+shp	Shipibo-Conibo
+sna	Shona
+cjs	Shor
+jiv	Shuar
+snp	Siane
+sya	Siang
+sid	Sidamo
+snn	Siona
+sri	Siriano
+srx	Sirmauri
+sil	Sisaala, Tumulung
+sld	Sissala
+akp	Siwu
+xog	Soga
+som	Somali
+bmu	Somba-Siawari
+khq	Songhay, Koyra Chiini
+ses	Songhay, Koyraboro Senni
+mnx	Sougb
+spa	Spanish
+srn	Sranan Tongo
+sxb	Suba
+suc	Subanon, Western
+tgo	Sudest
+suk	Sukuma
+sun	Sunda
+suz	Sunwar
+sgj	Surgujia
+sus	Susu
+swh	Swahili
+swe	Swedish
+syl	Sylheti
+dyi	Sénoufo, Djimini
+myk	Sénoufo, Mamara
+spp	Sénoufo, Supyire
+tap	Taabwa
+tby	Tabaru
+tna	Tacana
+shi	Tachelhit
+klw	Tado
+tgl	Tagalog
+tbk	Tagbanwa, Calamian
+tgj	Tagin
+blt	Tai Dam
+tbg	Tairora, North
+omw	Tairora, South
+tgk	Tajik
+tdj	Tajio
+tbc	Takia
+tlj	Talinga-Bwisi
+tly	Talysh
+ttq-script_tifinagh	Tamajaq, Tawallammat
+taj	Tamang, Eastern
+taq	Tamasheq
+tam	Tamil
+tpm	Tampulma
+tgp	Tangoa
+tnn	Tanna, North
+tac	Tarahumara, Western
+rif-script_latin	Tarifit
+rif-script_arabic	Tarifit
+tat	Tatar
+tav	Tatuyo
+twb	Tawbuid
+tbl	Tboli
+kps	Tehit
+twe	Teiwa
+ttc	Tektiteko
+tel	Telugu
+kdh	Tem
+tes	Tengger
+tex	Tennet
+tee	Tepehua, Huehuetla
+tpp	Tepehua, Pisaflores
+tpt	Tepehua, Tlachichilco
+stp	Tepehuan, Southeastern
+tfr	Teribe
+twu	Termanu
+ter	Terêna
+tew	Tewa
+thl	Tharu, Dangaura
+tem	Themne
+adx	Tibetan, Amdo
+bod	Tibetan, Central
+khg	Tibetan, Khams
+tca	Ticuna
+tir	Tigrigna
+txq	Tii
+tik	Tikar
+dgr	Tlicho
+tob	Toba
+tmf	Toba-Maskoy
+tng	Tobanga
+tlb	Tobelo
+ood	Tohono O’odham
+tpi	Tok Pisin
+jic	Tol
+lbw	Tolaki
+txa	Tombonuo
+tom	Tombulu
+toh	Tonga
+tnt	Tontemboan
+sda	Toraja-Sa’dan
+tcs	Torres Strait Creole
+toc	Totonac, Coyutla
+tos	Totonac, Highland
+neb	Toura
+trn	Trinitario
+trs	Triqui, Chicahuaxtla
+trc	Triqui, Copala
+tri	Trió
+cof	Tsafiki
+tkr	Tsakhur
+kdl	Tsikimba
+cas	Tsimané
+tso	Tsonga
+tuo	Tucano
+iou	Tuma-Irumu
+tmc	Tumak
+tuf	Tunebo, Central
+tur	Turkish
+tuk-script_latin	Turkmen
+tuk-script_arabic	Turkmen
+bov	Tuwuli
+tue	Tuyuca
+kcg	Tyap
+tzh-dialect_bachajón	Tzeltal
+tzh-dialect_tenejapa	Tzeltal
+tzo-dialect_chenalhó	Tzotzil
+tzo-dialect_chamula	Tzotzil
+tzj-dialect_western	Tz’utujil
+tzj-dialect_eastern	Tz’utujil
+aoz	Uab Meto
+udm	Udmurt
+udu	Uduk
+ukr	Ukrainian
+ppk	Uma
+ubu	Umbu-Ungu
+urk	Urak Lawoi’
+ura	Urarina
+urt	Urat
+urd-script_devanagari	Urdu
+urd-script_arabic	Urdu
+urd-script_latin	Urdu
+upv	Uripiv-Wala-Rano-Atchin
+usp	Uspanteko
+uig-script_arabic	Uyghur
+uig-script_cyrillic	Uyghur
+uzb-script_cyrillic	Uzbek
+vag	Vagla
+bav	Vengo
+vid	Vidunda
+vif	Vili
+vun	Vunjo
+vut	Vute
+prk	Wa, Parauk
+wwa	Waama
+rro	Waima
+bao	Waimaha
+waw	Waiwai
+lgl	Wala
+wlx	Wali
+cou	Wamey
+hub	Wampís
+gvc	Wanano
+mfi	Wandala
+wap	Wapishana
+wba	Warao
+war	Waray-Waray
+way	Wayana
+guc	Wayuu
+cym	Welsh
+kvw	Wersing
+tnp	Whitesands
+hto	Witoto, Minika
+huu	Witoto, Murui
+wal-script_latin	Wolaytta
+wal-script_ethiopic	Wolaytta
+wlo	Wolio
+noa	Woun Meu
+wob	Wè Northern
+kao	Xaasongaxango
+xer	Xerénte
+yad	Yagua
+yka	Yakan
+sah	Yakut
+yba	Yala
+yli	Yali, Angguruk
+nlk	Yali, Ninia
+yal	Yalunka
+yam	Yamba
+yat	Yambeta
+jmd	Yamdena
+tao	Yami
+yaa	Yaminahua
+ame	Yanesha’
+guu	Yanomamö
+yao	Yao
+yre	Yaouré
+yva	Yawa
+ybb	Yemba
+pib	Yine
+byr	Yipma
+pil	Yom
+yor	Yoruba
+ycn	Yucuna
+ess	Yupik, Saint Lawrence Island
+yuz	Yuracare
+atb	Zaiwa
+zne	Zande
+zaq	Zapotec, Aloápam
+zpo	Zapotec, Amatlán
+zad	Zapotec, Cajonos
+zpc	Zapotec, Choapan
+zca	Zapotec, Coatecas Altas
+zpg	Zapotec, Guevea de Humboldt
+zai	Zapotec, Isthmus
+zpl	Zapotec, Lachixío
+zam	Zapotec, Miahuatlán
+zaw	Zapotec, Mitla
+zpm	Zapotec, Mixtepec
+zac	Zapotec, Ocotlán
+zao	Zapotec, Ozolotepec
+ztq	Zapotec, Quioquitani-Quierí
+zar	Zapotec, Rincón
+zpt	Zapotec, San Vicente Coatlán
+zpi	Zapotec, Santa María Quiegolani
+zas	Zapotec, Santo Domingo Albarradas
+zaa	Zapotec, Sierra de Juárez
+zpz	Zapotec, Texmelucan
+zab	Zapotec, Western Tlacolula Valley
+zpu	Zapotec, Yalálag
+zae	Zapotec, Yareni
+zty	Zapotec, Yatee
+zav	Zapotec, Yatzachi
+zza	Zaza
+zyb	Zhuang, Yongbei
+ziw	Zigula
+zos	Zoque, Francisco León
+gnd	Zulgo-Gemzek
+ewe	Éwé

mm_num2word.py

@@ -0,0 +1,142 @@
+"""
+This file is adapted from https://github.com/hpbyte/Myanmar_Number_to_Words
+"""
+import re
+
+mm_digit = {
+    "၀": "သုည",
+    "၁": "တစ်",
+    "၂": "နှစ်",
+    "၃": "သုံ:",
+    "၄": "လေ:",
+    "၅": "ငါ:",
+    "၆": "ခြောက်",
+    "၇": "ခုနှစ်",
+    "၈": "ရှစ်",
+    "၉": "ကို:",
+}
+
+# regular expressions
+rgxPh = "^(၀၁|၀၉)"
+rgxDate = "[၀-၉]{1,2}-[၀-၉]{1,2}-[၀-၉]{4}|[၀-၉]{1,2}\/[၀-၉]{1,2}\/[၀-၉]{4}"
+rgxTime = "[၀-၉]{1,2}:[၀-၉]{1,2}"
+rgxDec = "[၀-၉]*\.[၀-၉]*"
+rgxAmt = "[,၀-၉]+"
+
+
+def convert_digit(num):
+    """
+    @type     num   str
+    @param    num   Myanmar number
+    @rtype          str
+    @return         converted Myanmar spoken words
+    """
+
+    converted = ""
+    nb_digits = len(num)
+
+    def check_if_zero(pos):
+        return not num[-pos] == "၀"
+
+    def hundred_thousandth_val():
+        n = num[:-5]
+        return (
+            ("သိန်: " + mm_num2word(n))
+            if (n[-2:] == "၀၀")
+            else (mm_num2word(n) + "သိန်: ")
+        )
+
+    def thousandth_val():
+        return mm_digit[num[-4]] + ("ထောင် " if (num[-3:] == "၀၀၀") else "ထောင့် ")
+
+    def hundredth_val():
+        return mm_digit[num[-3]] + (
+            "ရာ့ "
+            if (
+                (num[-2] == "၀" and re.match(r"[၁-၉]", num[-1]))
+                or (re.match(r"[၁-၉]", num[-2]) and num[-1] == "၀")
+            )
+            else "ရာ "
+        )
+
+    def tenth_val():
+        return ("" if (num[-2] == "၁") else mm_digit[num[-2]]) + (
+            "ဆယ် " if (num[-1] == "၀") else "ဆယ့် "
+        )
+
+    if nb_digits > 5:
+        converted += hundred_thousandth_val()
+    if (nb_digits > 4) and check_if_zero(5):
+        converted += mm_digit[num[-5]] + "သောင်: "
+    if (nb_digits > 3) and check_if_zero(4):
+        converted += thousandth_val()
+    if (nb_digits > 2) and check_if_zero(3):
+        converted += hundredth_val()
+    if (nb_digits > 1) and check_if_zero(2):
+        converted += tenth_val()
+    if (nb_digits > 0) and check_if_zero(1):
+        converted += mm_digit[num[-1]]
+
+    return converted
+
+
+def mm_num2word(num):
+    """
+    Detect type of number and convert accordingly
+
+    @type     num   str
+    @param    num   Myanmar number
+    @rtype          str
+    @return         converted Myanmar spoken words
+    """
+
+    word = ""
+
+    # phone number
+    if re.match(r"" + rgxPh, num[:2]):
+        word = " ".join([(mm_digit[d] if not d == "၇" else "ခွန်") for d in num])
+    # date
+    elif re.match(r"" + rgxDate, num):
+        n = re.split(r"-|/", num)
+        word = (
+            convert_digit(n[-1])
+            + " ခုနှစ် "
+            + convert_digit(n[1])
+            + " လပိုင်: "
+            + convert_digit(n[0])
+            + " ရက်"
+        )
+    # time
+    elif re.match(r"" + rgxTime, num):
+        n = re.split(r":", num)
+        word = (convert_digit(n[0]) + " နာရီ ") + (
+            "ခွဲ" if (n[1] == "၃၀") else (convert_digit(n[1]) + " မိနစ်")
+        )
+    # decimal
+    elif re.match(r"" + rgxDec, num):
+        n = re.split(r"\.", num)
+        word = convert_digit(n[0]) + " ဒဿမ " + " ".join([mm_digit[d] for d in n[1]])
+    # amount
+    elif re.match(r"" + rgxAmt, num):
+        word = convert_digit(num.replace(",", ""))
+    # default
+    else:
+        raise Exception("Cannot convert the provided number format!")
+
+    return word
+
+
+def extract_num(S):
+    """
+    Extract numbers from the input string
+
+    @type     S   str
+    @param    S   Myanmar sentence
+    @rtype        list
+    @return       a list of Myanmar numbers
+    """
+    matchedNums = re.compile(
+        "%s|%s|%s|%s" % (rgxDate, rgxTime, rgxDec, rgxAmt)
+    ).findall(S)
+
+    return matchedNums

num2words_lang_map.json

@@ -0,0 +1,29 @@
+{
+    "eng": ["en", "English, default"],
+    "amh": ["am", "Amharic"],
+    "ara": ["ar", "Arabic"],
+    "deu": ["de", "German"],
+    "spa": ["es", "Spanish"],
+    "fas": ["fa", "Farsi"],
+    "fin": ["fi", "Finnish"],
+    "fra": ["fr", "French"],
+    "heb": ["he", "Hebrew"],
+    "hun": ["hu", "Hungarian"],
+    "ind": ["id", "Indonesian"],
+    "isl": ["is", "Icelandic"],
+    "kan": ["kn", "Kannada"],
+    "kor": ["ko", "Korean"],
+    "kaz": ["kz", "Kazakh"],
+    "lav": ["lv", "Latvian"],
+    "pol": ["pl", "Polish"],
+    "swe": ["sv", "Swedish"],
+    "ron": ["ro", "Romanian"],
+    "rus": ["ru", "Russian"],
+    "tel": ["te", "Telugu"],
+    "tgk": ["tg", "Tajik"],
+    "tur": ["tr", "Turkish"],
+    "tha": ["th", "Thai"],
+    "vie": ["vi", "Vietnamese"],
+    "nld": ["nl", "Dutch"],
+    "ukr": ["uk", "Ukrainian"]
+  }

requirements.txt

@@ -0,0 +1,5 @@
+ttsmms
+underthesea
+nltk
+soundfile
+num2words

test.py

@@ -0,0 +1,19 @@
+from collections import OrderedDict
+
+lang_codes = OrderedDict()
+
+with open("lang_code.txt", "r") as file:
+    for line in file:
+        line = line.strip()
+        if line.startswith("----"):
+            continue
+        iso, lang = line.split("\t", 1)
+        lang_codes[lang + "(" + iso + ")"] = iso
+
+# print(lang_codes)
+print(len(lang_codes))
+
+language_names = list(lang_codes.keys())
+
+print(language_names)
+print(lang_codes[language_names[0]])