Duplicate from facebook/mms-tts

Co-authored-by: Vineel Pratap <vineelpratap@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

README.md

@@ -0,0 +1,1206 @@
+---
+license: cc-by-nc-4.0
+inference: false
+tags:
+- mms
+- vits
+pipeline_tag: text-to-speech
+---
+
+# Massively Multilingual Speech (MMS) : Text-to-Speech Models
+
+This repository contains a collection of text-to-speech (TTS) models, offering support for over 1000 languages. These models are part of Facebook's [Massively Multilingual Speech](https://arxiv.org/abs/2305.13516) project, aiming to provide speech technology across a diverse range of languages.  
+
+## Table Of Contents
+
+- [Usage](#usage)
+- [Supported Languages](#supported-languages)
+- [Model details](#model-details)
+- [Additional links](#additional-links)
+  
+## Usage 
+For detailed instructions on utilizing the models, please refer to the [fairseq docs](https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md#tts-1). Additionally, you can explore the models on [MMS Space](https://huggingface.co/spaces/facebook/MMS) available on HuggingFace.
+
+*models* folder consists of only generator, which is enough to run TTS inference. Full model checkpoint which also includes the discriminator and the optimizer states can be found in *full_models* folder. The models can be downloaded locally using *[hf_hub_download](https://huggingface.co/docs/huggingface_hub/guides/download)* API.
+
+See [this section](https://github.com/facebookresearch/fairseq/blob/main/examples/mms/README.md#tts-1) for instructions on using the models for inference. 
+
+## Supported Languages
+
+This model supports 1107 languages. Unclick the following to toogle all supported languages of this checkpoint in [ISO 639-3 code](https://en.wikipedia.org/wiki/ISO_639-3).
+You can find more details about the languages and their ISO 639-3 codes in the [MMS Language Coverage Overview](https://dl.fbaipublicfiles.com/mms/misc/language_coverage_mms.html).
+<details>
+  <summary>Click to toggle</summary>
+
+ - abi
+ - ace
+ - aca
+ - acn
+ - acr
+ - ach
+ - acu
+ - guq
+ - ade
+ - adj
+ - agd
+ - agx
+ - agn
+ - aha
+ - aka
+ - knj
+ - ake
+ - aeu
+ - ahk
+ - bss
+ - alj
+ - sqi
+ - alt
+ - alp
+ - alz
+ - kab
+ - amk
+ - mmg
+ - amh
+ - ami
+ - azg
+ - agg
+ - boj
+ - cko
+ - any
+ - arl
+ - ara
+ - atq
+ - luc
+ - hyw
+ - apr
+ - aia
+ - msy
+ - cni
+ - cjo
+ - cpu
+ - cpb
+ - asm
+ - asa
+ - teo
+ - ati
+ - djk
+ - ava
+ - avn
+ - avu
+ - awb
+ - kwi
+ - awa
+ - agr
+ - agu
+ - ayr
+ - ayo
+ - abp
+ - blx
+ - sgb
+ - azj-script_cyrillic
+ - azj-script_latin
+ - azb
+ - bba
+ - bhz
+ - bvc
+ - bfy
+ - bgq
+ - bdq
+ - bdh
+ - bqi
+ - bjw
+ - blz
+ - ban
+ - bcc-script_latin
+ - bcc-script_arabic
+ - bam
+ - ptu
+ - bcw
+ - bqj
+ - bno
+ - bbb
+ - bfa
+ - bjz
+ - bak
+ - eus
+ - bsq
+ - akb
+ - btd
+ - btx
+ - bts
+ - bbc
+ - bvz
+ - bjv
+ - bep
+ - bkv
+ - bzj
+ - bem
+ - bng
+ - ben
+ - bom
+ - btt
+ - bha
+ - bgw
+ - bht
+ - beh
+ - sne
+ - ubl
+ - bcl
+ - bim
+ - bkd
+ - bjr
+ - bfo
+ - biv
+ - bib
+ - bis
+ - bzi
+ - bqp
+ - bpr
+ - bps
+ - bwq
+ - bdv
+ - bqc
+ - bus
+ - bnp
+ - bmq
+ - bdg
+ - boa
+ - ksr
+ - bor
+ - bru
+ - box
+ - bzh
+ - bgt
+ - sab
+ - bul
+ - bwu
+ - bmv
+ - mya
+ - tte
+ - cjp
+ - cbv
+ - kaq
+ - cot
+ - cbc
+ - car
+ - cat
+ - ceb
+ - cme
+ - cbi
+ - ceg
+ - cly
+ - cya
+ - che
+ - hne
+ - nya
+ - dig
+ - dug
+ - bgr
+ - cek
+ - cfm
+ - cnh
+ - hlt
+ - mwq
+ - ctd
+ - tcz
+ - zyp
+ - cco
+ - cnl
+ - cle
+ - chz
+ - cpa
+ - cso
+ - cnt
+ - cuc
+ - hak
+ - nan
+ - xnj
+ - cap
+ - cax
+ - ctg
+ - ctu
+ - chf
+ - cce
+ - crt
+ - crq
+ - cac-dialect_sansebastiáncoatán
+ - cac-dialect_sanmateoixtatán
+ - ckt
+ - ncu
+ - cdj
+ - chv
+ - caa
+ - asg
+ - con
+ - crn
+ - cok
+ - crk-script_latin
+ - crk-script_syllabics
+ - crh
+ - cui
+ - dsh
+ - dbq
+ - dga
+ - dgi
+ - dgk
+ - dnj-dialect_gweetaawueast
+ - dnj-dialect_blowowest
+ - daa
+ - dnt
+ - dnw
+ - dar
+ - tcc
+ - dwr
+ - ded
+ - mzw
+ - ntr
+ - ddn
+ - des
+ - dso
+ - nfa
+ - dhi
+ - gud
+ - did
+ - mhu
+ - dip
+ - dik
+ - tbz
+ - dts
+ - dos
+ - dgo
+ - mvp
+ - nld
+ - jen
+ - dzo
+ - idd
+ - eka
+ - cto
+ - emp
+ - eng
+ - enx
+ - sja
+ - myv
+ - mcq
+ - ese
+ - evn
+ - eza
+ - fal
+ - fao
+ - far
+ - fij
+ - fin
+ - fon
+ - frd
+ - fra
+ - ful
+ - flr
+ - gau
+ - gbk
+ - gag-script_cyrillic
+ - gag-script_latin
+ - gbi
+ - gmv
+ - lug
+ - pwg
+ - gbm
+ - cab
+ - grt
+ - krs
+ - gso
+ - nlg
+ - gej
+ - deu
+ - gri
+ - kik
+ - acd
+ - glk
+ - gof-script_latin
+ - gog
+ - gkn
+ - wsg
+ - gjn
+ - gqr
+ - gor
+ - gux
+ - gbo
+ - ell
+ - grc
+ - guh
+ - gub
+ - grn
+ - gyr
+ - guo
+ - gde
+ - guj
+ - gvl
+ - guk
+ - rub
+ - dah
+ - gwr
+ - gwi
+ - hat
+ - hlb
+ - amf
+ - hag
+ - hnn
+ - bgc
+ - had
+ - hau
+ - hwc
+ - hvn
+ - hay
+ - xed
+ - heb
+ - heh
+ - hil
+ - hin
+ - hif
+ - hns
+ - hoc
+ - hoy
+ - hus-dialect_westernpotosino
+ - hus-dialect_centralveracruz
+ - huv
+ - hui
+ - hun
+ - hap
+ - iba
+ - isl
+ - dbj
+ - ifa
+ - ifb
+ - ifu
+ - ifk
+ - ife
+ - ign
+ - ikk
+ - iqw
+ - ilb
+ - ilo
+ - imo
+ - ind
+ - inb
+ - ipi
+ - irk
+ - icr
+ - itv
+ - itl
+ - atg
+ - ixl-dialect_sanjuancotzal
+ - ixl-dialect_sangasparchajul
+ - ixl-dialect_santamarianebaj
+ - nca
+ - izr
+ - izz
+ - jac
+ - jam
+ - jav
+ - jvn
+ - kac
+ - dyo
+ - csk
+ - adh
+ - jun
+ - jbu
+ - dyu
+ - bex
+ - juy
+ - gna
+ - urb
+ - kbp
+ - cwa
+ - dtp
+ - kbr
+ - cgc
+ - kki
+ - kzf
+ - lew
+ - cbr
+ - kkj
+ - keo
+ - kqe
+ - kak
+ - kyb
+ - knb
+ - kmd
+ - kml
+ - ify
+ - xal
+ - kbq
+ - kay
+ - ktb
+ - hig
+ - gam
+ - cbu
+ - xnr
+ - kmu
+ - kne
+ - kan
+ - kby
+ - pam
+ - cak-dialect_santamaríadejesús
+ - cak-dialect_southcentral
+ - cak-dialect_yepocapa
+ - cak-dialect_western
+ - cak-dialect_santodomingoxenacoj
+ - cak-dialect_central
+ - xrb
+ - krc
+ - kaa
+ - krl
+ - pww
+ - xsm
+ - cbs
+ - pss
+ - kxf
+ - kyz
+ - kyu
+ - txu
+ - kaz
+ - ndp
+ - kbo
+ - kyq
+ - ken
+ - ker
+ - xte
+ - kyg
+ - kjh
+ - kca
+ - khm
+ - kxm
+ - kjg
+ - nyf
+ - kij
+ - kia
+ - kqr
+ - kqp
+ - krj
+ - zga
+ - kin
+ - pkb
+ - geb
+ - gil
+ - kje
+ - kss
+ - thk
+ - klu
+ - kyo
+ - kog
+ - kfb
+ - kpv
+ - bbo
+ - xon
+ - kma
+ - kno
+ - kxc
+ - ozm
+ - kqy
+ - kor
+ - coe
+ - kpq
+ - kpy
+ - kyf
+ - kff-script_telugu
+ - kri
+ - rop
+ - ktj
+ - ted
+ - krr
+ - kdt
+ - kez
+ - cul
+ - kle
+ - kdi
+ - kue
+ - kum
+ - kvn
+ - cuk
+ - kdn
+ - xuo
+ - key
+ - kpz
+ - knk
+ - kmr-script_latin
+ - kmr-script_arabic
+ - kmr-script_cyrillic
+ - xua
+ - kru
+ - kus
+ - kub
+ - kdc
+ - kxv
+ - blh
+ - cwt
+ - kwd
+ - tnk
+ - kwf
+ - cwe
+ - kyc
+ - tye
+ - kir
+ - quc-dialect_north
+ - quc-dialect_east
+ - quc-dialect_central
+ - lac
+ - lsi
+ - lbj
+ - lhu
+ - las
+ - lam
+ - lns
+ - ljp
+ - laj
+ - lao
+ - lat
+ - lav
+ - law
+ - lcp
+ - lzz
+ - lln
+ - lef
+ - acf
+ - lww
+ - mhx
+ - eip
+ - lia
+ - lif
+ - onb
+ - lis
+ - loq
+ - lob
+ - yaz
+ - lok
+ - llg
+ - ycl
+ - lom
+ - ngl
+ - lon
+ - lex
+ - lgg
+ - ruf
+ - dop
+ - lnd
+ - ndy
+ - lwo
+ - lee
+ - mev
+ - mfz
+ - jmc
+ - myy
+ - mbc
+ - mda
+ - mad
+ - mag
+ - ayz
+ - mai
+ - mca
+ - mcp
+ - mak
+ - vmw
+ - mgh
+ - kde
+ - mlg
+ - zlm
+ - pse
+ - mkn
+ - xmm
+ - mal
+ - xdy
+ - div
+ - mdy
+ - mup
+ - mam-dialect_central
+ - mam-dialect_northern
+ - mam-dialect_southern
+ - mam-dialect_western
+ - mqj
+ - mcu
+ - mzk
+ - maw
+ - mjl
+ - mnk
+ - mge
+ - mbh
+ - knf
+ - mjv
+ - mbt
+ - obo
+ - mbb
+ - mzj
+ - sjm
+ - mrw
+ - mar
+ - mpg
+ - mhr
+ - enb
+ - mah
+ - myx
+ - klv
+ - mfh
+ - met
+ - mcb
+ - mop
+ - yua
+ - mfy
+ - maz
+ - vmy
+ - maq
+ - mzi
+ - maj
+ - maa-dialect_sanantonio
+ - maa-dialect_sanjerónimo
+ - mhy
+ - mhi
+ - zmz
+ - myb
+ - gai
+ - mqb
+ - mbu
+ - med
+ - men
+ - mee
+ - mwv
+ - meq
+ - zim
+ - mgo
+ - mej
+ - mpp
+ - min
+ - gum
+ - mpx
+ - mco
+ - mxq
+ - pxm
+ - mto
+ - mim
+ - xta
+ - mbz
+ - mip
+ - mib
+ - miy
+ - mih
+ - miz
+ - xtd
+ - mxt
+ - xtm
+ - mxv
+ - xtn
+ - mie
+ - mil
+ - mio
+ - mdv
+ - mza
+ - mit
+ - mxb
+ - mpm
+ - soy
+ - cmo-script_latin
+ - cmo-script_khmer
+ - mfq
+ - old
+ - mfk
+ - mif
+ - mkl
+ - mox
+ - myl
+ - mqf
+ - mnw
+ - mon
+ - mog
+ - mfe
+ - mor
+ - mqn
+ - mgd
+ - mtj
+ - cmr
+ - mtd
+ - bmr
+ - moz
+ - mzm
+ - mnb
+ - mnf
+ - unr
+ - fmu
+ - mur
+ - tih
+ - muv
+ - muy
+ - sur
+ - moa
+ - wmw
+ - tnr
+ - miq
+ - mos
+ - muh
+ - nas
+ - mbj
+ - nfr
+ - kfw
+ - nst
+ - nag
+ - nch
+ - nhe
+ - ngu
+ - azz
+ - nhx
+ - ncl
+ - nhy
+ - ncj
+ - nsu
+ - npl
+ - nuz
+ - nhw
+ - nhi
+ - nlc
+ - nab
+ - gld
+ - nnb
+ - npy
+ - pbb
+ - ntm
+ - nmz
+ - naw
+ - nxq
+ - ndj
+ - ndz
+ - ndv
+ - new
+ - nij
+ - sba
+ - gng
+ - nga
+ - nnq
+ - ngp
+ - gym
+ - kdj
+ - nia
+ - nim
+ - nin
+ - nko
+ - nog
+ - lem
+ - not
+ - nhu
+ - bud
+ - nus
+ - yas
+ - nnw
+ - nwb
+ - nyy
+ - nyn
+ - rim
+ - lid
+ - nuj
+ - nyo
+ - nzi
+ - ann
+ - ory
+ - ojb-script_latin
+ - ojb-script_syllabics
+ - oku
+ - bsc
+ - bdu
+ - orm
+ - ury
+ - oss
+ - ote
+ - otq
+ - stn
+ - sig
+ - kfx
+ - bfz
+ - sey
+ - pao
+ - pau
+ - pce
+ - plw
+ - pmf
+ - pag
+ - pap
+ - prf
+ - pab
+ - pbi
+ - pbc
+ - pad
+ - ata
+ - pez
+ - peg
+ - fas
+ - pcm
+ - pis
+ - pny
+ - pir
+ - pjt
+ - poy
+ - pol
+ - pps
+ - pls
+ - poi
+ - poh-dialect_eastern
+ - poh-dialect_western
+ - por
+ - prt
+ - pui
+ - pan
+ - tsz
+ - suv
+ - lme
+ - quy
+ - qvc
+ - quz
+ - qve
+ - qub
+ - qvh
+ - qwh
+ - qvw
+ - quf
+ - qvm
+ - qul
+ - qvn
+ - qxn
+ - qxh
+ - qvs
+ - quh
+ - qxo
+ - qxr
+ - qvo
+ - qvz
+ - qxl
+ - quw
+ - kjb
+ - kek
+ - rah
+ - rjs
+ - rai
+ - lje
+ - rnl
+ - rkt
+ - rap
+ - yea
+ - raw
+ - rej
+ - rel
+ - ril
+ - iri
+ - rgu
+ - rhg
+ - rmc-script_latin
+ - rmc-script_cyrillic
+ - rmo
+ - rmy-script_latin
+ - rmy-script_cyrillic
+ - ron
+ - rol
+ - cla
+ - rng
+ - rug
+ - run
+ - rus
+ - lsm
+ - spy
+ - sck
+ - saj
+ - sch
+ - sml
+ - xsb
+ - sbl
+ - saq
+ - sbd
+ - smo
+ - rav
+ - sxn
+ - sag
+ - sbp
+ - xsu
+ - srm
+ - sas
+ - apb
+ - sgw
+ - tvw
+ - lip
+ - slu
+ - snw
+ - sea
+ - sza
+ - seh
+ - crs
+ - ksb
+ - shn
+ - sho
+ - mcd
+ - cbt
+ - xsr
+ - shk
+ - shp
+ - sna
+ - cjs
+ - jiv
+ - snp
+ - sya
+ - sid
+ - snn
+ - sri
+ - srx
+ - sil
+ - sld
+ - akp
+ - xog
+ - som
+ - bmu
+ - khq
+ - ses
+ - mnx
+ - spa
+ - srn
+ - sxb
+ - suc
+ - tgo
+ - suk
+ - sun
+ - suz
+ - sgj
+ - sus
+ - swh
+ - swe
+ - syl
+ - dyi
+ - myk
+ - spp
+ - tap
+ - tby
+ - tna
+ - shi
+ - klw
+ - tgl
+ - tbk
+ - tgj
+ - blt
+ - tbg
+ - omw
+ - tgk
+ - tdj
+ - tbc
+ - tlj
+ - tly
+ - ttq-script_tifinagh
+ - taj
+ - taq
+ - tam
+ - tpm
+ - tgp
+ - tnn
+ - tac
+ - rif-script_latin
+ - rif-script_arabic
+ - tat
+ - tav
+ - twb
+ - tbl
+ - kps
+ - twe
+ - ttc
+ - tel
+ - kdh
+ - tes
+ - tex
+ - tee
+ - tpp
+ - tpt
+ - stp
+ - tfr
+ - twu
+ - ter
+ - tew
+ - tha
+ - nod
+ - thl
+ - tem
+ - adx
+ - bod
+ - khg
+ - tca
+ - tir
+ - txq
+ - tik
+ - dgr
+ - tob
+ - tmf
+ - tng
+ - tlb
+ - ood
+ - tpi
+ - jic
+ - lbw
+ - txa
+ - tom
+ - toh
+ - tnt
+ - sda
+ - tcs
+ - toc
+ - tos
+ - neb
+ - trn
+ - trs
+ - trc
+ - tri
+ - cof
+ - tkr
+ - kdl
+ - cas
+ - tso
+ - tuo
+ - iou
+ - tmc
+ - tuf
+ - tur
+ - tuk-script_latin
+ - tuk-script_arabic
+ - bov
+ - tue
+ - kcg
+ - tzh-dialect_bachajón
+ - tzh-dialect_tenejapa
+ - tzo-dialect_chenalhó
+ - tzo-dialect_chamula
+ - tzj-dialect_western
+ - tzj-dialect_eastern
+ - aoz
+ - udm
+ - udu
+ - ukr
+ - ppk
+ - ubu
+ - urk
+ - ura
+ - urt
+ - urd-script_devanagari
+ - urd-script_arabic
+ - urd-script_latin
+ - upv
+ - usp
+ - uig-script_arabic
+ - uig-script_cyrillic
+ - uzb-script_cyrillic
+ - vag
+ - bav
+ - vid
+ - vie
+ - vif
+ - vun
+ - vut
+ - prk
+ - wwa
+ - rro
+ - bao
+ - waw
+ - lgl
+ - wlx
+ - cou
+ - hub
+ - gvc
+ - mfi
+ - wap
+ - wba
+ - war
+ - way
+ - guc
+ - cym
+ - kvw
+ - tnp
+ - hto
+ - huu
+ - wal-script_latin
+ - wal-script_ethiopic
+ - wlo
+ - noa
+ - wob
+ - kao
+ - xer
+ - yad
+ - yka
+ - sah
+ - yba
+ - yli
+ - nlk
+ - yal
+ - yam
+ - yat
+ - jmd
+ - tao
+ - yaa
+ - ame
+ - guu
+ - yao
+ - yre
+ - yva
+ - ybb
+ - pib
+ - byr
+ - pil
+ - yor
+ - ycn
+ - ess
+ - yuz
+ - atb
+ - zne
+ - zaq
+ - zpo
+ - zad
+ - zpc
+ - zca
+ - zpg
+ - zai
+ - zpl
+ - zam
+ - zaw
+ - zpm
+ - zac
+ - zao
+ - ztq
+ - zar
+ - zpt
+ - zpi
+ - zas
+ - zaa
+ - zpz
+ - zab
+ - zpu
+ - zae
+ - zty
+ - zav
+ - zza
+ - zyb
+ - ziw
+ - zos
+ - gnd
+ - ewe
+
+</details>
+
+## Model details
+
+- **Developed by:** Vineel Pratap et al.
+- **Model type:** Text-to-speech model
+- **Language(s):** 1107 languages, see [supported languages](#supported-languages)
+- **License:** CC-BY-NC 4.0 license
+- **Cite as:**
+
+      @article{pratap2023mms,
+        title={Scaling Speech Technology to 1,000+ Languages},
+        author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli},
+      journal={arXiv},
+      year={2023}
+      }
+
+## Additional Links
+
+- [Blog post](https://ai.facebook.com/blog/multilingual-model-speech-recognition/)
+- [Transformers documentation](https://huggingface.co/docs/transformers/main/en/model_doc/mms).
+- [Paper](https://arxiv.org/abs/2305.13516)
+- [GitHub Repository](https://github.com/facebookresearch/fairseq/tree/main/examples/mms#asr)
+- [Other **MMS** checkpoints](https://huggingface.co/models?other=mms)
+- MMS base checkpoints:
+  - [facebook/mms-1b](https://huggingface.co/facebook/mms-1b)
+  - [facebook/mms-300m](https://huggingface.co/facebook/mms-300m)
+- [Official Space](https://huggingface.co/spaces/facebook/MMS)

full_models/abi/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0be668a16e5b9b9dedd41e08442644f4ed894e4c62f43d06e7e448158428e2fe
+size 561098185

full_models/abi/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bee8bd93805bd44cee1ff5497bc3a87220eeeec8b0fd6a2368d0609001a2868
+size 436570305

full_models/abi/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/abi/vocab.txt

@@ -0,0 +1,53 @@
+ɔ
+ê
+ǒ
+ 
+̂
+h
+ě
+i
+ɩ
+k
+á
+̌
+ǐ
+b
+p
+í
+ǔ
+u
+ń
+w
+'
+ί
+f
+ó
+y
+s
+î
+m
+ɛ
+έ
+e
+ʋ
+ḿ
+n
+ú
+o
+d
+â
+ô
+c
+ǎ
+é
+́
+j
+l
+-
+t
+_
+r
+g
+ε
+û
+a

full_models/abp/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3176637b067b5fc78605aff0b553ec09244da37ebbff3f419163cede7824c441
+size 561098185

full_models/abp/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f621739a139733b14ac70f032ab4a677e8912fa3a1132ba3f8cf599dee6dbbac
+size 436524225

full_models/abp/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/abp/vocab.txt

@@ -0,0 +1,33 @@
+_
+t
+e
+b
+ō
+j
+c
+r
+f
+w
+i
+q
+h
+g
+l
+m
+k
+y
+d
+ā
+s
+'
+a
+n
+x
+6
+o
+-
+p
+u
+ 
+v
+z

full_models/aca/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae308c0880cb4e3bd2d02600485b473f068c38ff85bac0a7d5bd8951ba1ce963
+size 561076199

full_models/aca/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78666df5cbdca3fbd91b2bb2f49841f8919b7a73ab6e504ed82f7597e41c190f
+size 436353726

full_models/aca/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/aca/vocab.txt

@@ -0,0 +1,35 @@
+a
+|
+i
+n
+á
+c
+e
+u
+l
+r
+w
+j
+s
+í
+m
+é
+o
+'
+h
+t
+y
+b
+d
+ú
+q
+ó
+p
+—
+g
+f
+z
+v
+x
+ñ
+ 

full_models/acd/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92c06f2853c68b0bc604a40caa9261cf439f0b02d66a510b08a0660b0f8e3201
+size 561078480

full_models/acd/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d3e15a2db968008b7b01eb6282b9c24115221f2abccd8935ee11a16d6f6cf9
+size 436355114

full_models/acd/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/acd/vocab.txt

@@ -0,0 +1,28 @@
+|
+a
+ɛ
+n
+ɔ
+i
+o
+m
+y
+e
+u
+g
+s
+k
+b
+r
+l
+d
+w
+f
+-
+t
+p
+'
+ŋ
+h
+c
+ 

full_models/ace/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecacad3f1f738085d053f35c5618c4abceaee39c28dbff2975e17fc918cea5c7
+size 561078594

full_models/ace/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:183895b264e9f91617ababbd088b5309ea79468730819506c8c8ab5e977085e6
+size 436387528

full_models/ace/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/ace/vocab.txt

@@ -0,0 +1,42 @@
+|
+a
+n
+e
+u
+g
+t
+h
+i
+k
+m
+b
+o
+y
+l
+r
+s
+p
+j
+d
+é
+w
+ô
+ë
+-
+c
+ö
+á
+ó
+f
+z
+'
+q
+ú
+`
+0
+6
+4
+3
+1
+2
+ 

full_models/acf/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:262ec2da7c0e7ded6eaa1cd84e37fe55127f23280d272d9453591df621511b21
+size 561078869

full_models/acf/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f23d7c73bfdf05bec98d6fc71dffbf19409a9afb463b6974abccdaee53c215
+size 436369451

full_models/acf/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/acf/vocab.txt

@@ -0,0 +1,33 @@
+|
+a
+n
+é
+i
+o
+s
+t
+k
+y
+p
+l
+w
+m
+è
+u
+d
+-
+e
+b
+v
+j
+ò
+z
+f
+ʼ
+h
+g
+c
+r
+—
+'
+ 

full_models/ach/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d772464b61e01ae7415ad3b4cae63851b5fd89c15b6157b311446e3f3ea7460c
+size 561078618

full_models/ach/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46031da7d624512421e115dcfadede182580c6c3139d2ea2b7c20b4fabee7e1d
+size 436355251

full_models/ach/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/ach/vocab.txt

@@ -0,0 +1,28 @@
+|
+o
+a
+i
+e
+k
+n
+m
+w
+t
+u
+y
+l
+c
+d
+b
+g
+r
+p
+ŋ
+j
+-
+s
+'
+v
+f
+h
+ 

full_models/acn/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c7c7622cba3d3aa313a67157d78898fcffb20dc0855d9c9ac93e544a79b11f3
+size 561098185

full_models/acn/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f608e1298f921bba8ebfa9e1eadb3c599aff4a0eb64614fb32a3d372340a9b4b
+size 436533441

full_models/acn/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/acn/vocab.txt

@@ -0,0 +1,37 @@
+u
+k
+g
+a
+_
+—
+d
+w
+i
+o
+-
+b
+e
+n
+t
+y
+p
+s
+z
+x
+m
+h
+c
+ 
+l
+0
+2
+j
+f
+3
+5
+q
+v
+r
+6
+1
+4

full_models/acr/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e790e6b73ad3a311ec0bd311e50a33846f38b8e63f074650687a6f588ea7df
+size 561078709

full_models/acr/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:892faf58e703daf31d96bd7b9913d2b0eda8f750305282ba760a656280a5437f
+size 436375881

full_models/acr/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/acr/vocab.txt

@@ -0,0 +1,37 @@
+|
+a
+i
+'
+k
+r
+u
+e
+j
+n
+o
+c
+l
+h
+t
+q
+w
+x
+m
+b
+s
+y
+p
+z
+d
+—
+ú
+g
+á
+é
+ó
+f
+í
+v
+-
+ñ
+ 

full_models/acu/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8f2db7fee9018cff7d22ff7ede80bfcfb408c2cb3a38a3ccf32f1594865969
+size 561078587

full_models/acu/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5952ecca5322b2410a5056b1852650d2fb9289f3cebce5e9b95a7ee76eabc621
+size 436371382

full_models/acu/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/acu/vocab.txt

@@ -0,0 +1,35 @@
+a
+|
+i
+n
+u
+t
+r
+m
+k
+s
+e
+h
+j
+c
+w
+y
+p
+g
+o
+í
+—
+ú
+d
+l
+é
+á
+b
+f
+v
+ó
+z
+q
+x
+ñ
+ 

full_models/ade/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41191e5d74955fec278ea692b2218c7920de8f16147aba556fdfce56b714f4c0
+size 561078757

full_models/ade/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aed6df678ce5a605da1adef5aa7016ec89dd3b209ffebad3156843473d688668
+size 436384590

full_models/ade/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/ade/vocab.txt

@@ -0,0 +1,40 @@
+|
+a
+â
+n
+e
+b
+g
+æ
+i
+t
+w
+ô
+y
+k
+o
+r
+l
+u
+d
+m
+f
+s
+û
+p
+à
+-
+è
+ã
+õ
+ù
+î
+å
+ì
+ü
+ǹ
+ò
+h
+'
+c
+ 

full_models/adh/D_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f466d6d8e81596e107e5e3ebb2f5fea640411555a9ae7a6b719bc80f0d11f42
+size 561078757

full_models/adh/G_100000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6a6d6796cd6997ca30c352c12f25d36db4d80ac374e42318aeba8a2ce1905a
+size 436360329

full_models/adh/config.json

@@ -0,0 +1,87 @@
+{
+    "train": {
+        "log_interval": 200,
+        "eval_interval": 1000,
+        "seed": 1234,
+        "epochs": 20000,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 64,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "train.ltr",
+        "validation_files": "dev.ltr",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 16000,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

full_models/adh/vocab.txt

@@ -0,0 +1,29 @@
+|
+o
+i
+a
+e
+n
+k
+m
+w
+r
+y
+h
+t
+d
+j
+g
+u
+l
+p
+c
+b
+ŋ
+s
+f
+'
+z
+v
+-
+