Duplicate from AsakuraMizu/moe-tts

Co-authored-by: Asakura Mizu <[email protected]>

.gitattributes

@@ -0,0 +1,35 @@
+*.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
+*.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
+*.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
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pb 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
+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
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.o filter=lfs diff=lfs merge=lfs -text
+*.dll filter=lfs diff=lfs merge=lfs -text
+*.so filter=lfs diff=lfs merge=lfs -text
+*.ocd2 filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,365 @@
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+##
+## Get latest from https://github.com/github/gitignore/blob/master/VisualStudio.gitignore
+
+# User-specific files
+*.rsuser
+*.suo
+*.user
+*.userosscache
+*.sln.docstates
+
+# User-specific files (MonoDevelop/Xamarin Studio)
+*.userprefs
+
+# Mono auto generated files
+mono_crash.*
+
+# Build results
+[Dd]ebug/
+[Dd]ebugPublic/
+[Rr]elease/
+[Rr]eleases/
+x64/
+x86/
+[Ww][Ii][Nn]32/
+[Aa][Rr][Mm]/
+[Aa][Rr][Mm]64/
+bld/
+[Bb]in/
+[Oo]bj/
+[Oo]ut/
+[Ll]og/
+[Ll]ogs/
+
+# Visual Studio 2015/2017 cache/options directory
+.vs/
+# Uncomment if you have tasks that create the project's static files in wwwroot
+#wwwroot/
+
+# Visual Studio 2017 auto generated files
+Generated\ Files/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+# NUnit
+*.VisualState.xml
+TestResult.xml
+nunit-*.xml
+
+# Build Results of an ATL Project
+[Dd]ebugPS/
+[Rr]eleasePS/
+dlldata.c
+
+# Benchmark Results
+BenchmarkDotNet.Artifacts/
+
+# .NET Core
+project.lock.json
+project.fragment.lock.json
+artifacts/
+
+# ASP.NET Scaffolding
+ScaffoldingReadMe.txt
+
+# StyleCop
+StyleCopReport.xml
+
+# Files built by Visual Studio
+*_i.c
+*_p.c
+*_h.h
+*.ilk
+*.meta
+*.obj
+*.iobj
+*.pch
+*.pdb
+*.ipdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*_wpftmp.csproj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.svclog
+*.scc
+
+# Chutzpah Test files
+_Chutzpah*
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opendb
+*.opensdf
+*.sdf
+*.cachefile
+*.VC.db
+*.VC.VC.opendb
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+*.sap
+
+# Visual Studio Trace Files
+*.e2e
+
+# TFS 2012 Local Workspace
+$tf/
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+*.DotSettings.user
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# AxoCover is a Code Coverage Tool
+.axoCover/*
+!.axoCover/settings.json
+
+# Coverlet is a free, cross platform Code Coverage Tool
+coverage*.json
+coverage*.xml
+coverage*.info
+
+# Visual Studio code coverage results
+*.coverage
+*.coveragexml
+
+# NCrunch
+_NCrunch_*
+.*crunch*.local.xml
+nCrunchTemp_*
+
+# MightyMoose
+*.mm.*
+AutoTest.Net/
+
+# Web workbench (sass)
+.sass-cache/
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.[Pp]ublish.xml
+*.azurePubxml
+# Note: Comment the next line if you want to checkin your web deploy settings,
+# but database connection strings (with potential passwords) will be unencrypted
+*.pubxml
+*.publishproj
+
+# Microsoft Azure Web App publish settings. Comment the next line if you want to
+# checkin your Azure Web App publish settings, but sensitive information contained
+# in these scripts will be unencrypted
+PublishScripts/
+
+# NuGet Packages
+*.nupkg
+# NuGet Symbol Packages
+*.snupkg
+# The packages folder can be ignored because of Package Restore
+**/[Pp]ackages/*
+# except build/, which is used as an MSBuild target.
+!**/[Pp]ackages/build/
+# Uncomment if necessary however generally it will be regenerated when needed
+#!**/[Pp]ackages/repositories.config
+# NuGet v3's project.json files produces more ignorable files
+*.nuget.props
+*.nuget.targets
+
+# Microsoft Azure Build Output
+csx/
+*.build.csdef
+
+# Microsoft Azure Emulator
+ecf/
+rcf/
+
+# Windows Store app package directories and files
+AppPackages/
+BundleArtifacts/
+Package.StoreAssociation.xml
+_pkginfo.txt
+*.appx
+*.appxbundle
+*.appxupload
+
+# Visual Studio cache files
+# files ending in .cache can be ignored
+*.[Cc]ache
+# but keep track of directories ending in .cache
+!?*.[Cc]ache/
+
+# Others
+ClientBin/
+~$*
+*~
+*.dbmdl
+*.dbproj.schemaview
+*.jfm
+*.pfx
+*.publishsettings
+orleans.codegen.cs
+
+# Including strong name files can present a security risk
+# (https://github.com/github/gitignore/pull/2483#issue-259490424)
+#*.snk
+
+# Since there are multiple workflows, uncomment next line to ignore bower_components
+# (https://github.com/github/gitignore/pull/1529#issuecomment-104372622)
+#bower_components/
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file
+# to a newer Visual Studio version. Backup files are not needed,
+# because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+ServiceFabricBackup/
+*.rptproj.bak
+
+# SQL Server files
+*.mdf
+*.ldf
+*.ndf
+
+# Business Intelligence projects
+*.rdl.data
+*.bim.layout
+*.bim_*.settings
+*.rptproj.rsuser
+*- [Bb]ackup.rdl
+*- [Bb]ackup ([0-9]).rdl
+*- [Bb]ackup ([0-9][0-9]).rdl
+
+# Microsoft Fakes
+FakesAssemblies/
+
+# GhostDoc plugin setting file
+*.GhostDoc.xml
+
+# Node.js Tools for Visual Studio
+.ntvs_analysis.dat
+node_modules/
+
+# Visual Studio 6 build log
+*.plg
+
+# Visual Studio 6 workspace options file
+*.opt
+
+# Visual Studio 6 auto-generated workspace file (contains which files were open etc.)
+*.vbw
+
+# Visual Studio LightSwitch build output
+**/*.HTMLClient/GeneratedArtifacts
+**/*.DesktopClient/GeneratedArtifacts
+**/*.DesktopClient/ModelManifest.xml
+**/*.Server/GeneratedArtifacts
+**/*.Server/ModelManifest.xml
+_Pvt_Extensions
+
+# Paket dependency manager
+.paket/paket.exe
+paket-files/
+
+# FAKE - F# Make
+.fake/
+
+# CodeRush personal settings
+.cr/personal
+
+# Python Tools for Visual Studio (PTVS)
+__pycache__/
+*.pyc
+
+# Cake - Uncomment if you are using it
+# tools/**
+# !tools/packages.config
+
+# Tabs Studio
+*.tss
+
+# Telerik's JustMock configuration file
+*.jmconfig
+
+# BizTalk build output
+*.btp.cs
+*.btm.cs
+*.odx.cs
+*.xsd.cs
+
+# OpenCover UI analysis results
+OpenCover/
+
+# Azure Stream Analytics local run output
+ASALocalRun/
+
+# MSBuild Binary and Structured Log
+*.binlog
+
+# NVidia Nsight GPU debugger configuration file
+*.nvuser
+
+# MFractors (Xamarin productivity tool) working folder
+.mfractor/
+
+# Local History for Visual Studio
+.localhistory/
+
+# BeatPulse healthcheck temp database
+healthchecksdb
+
+# Backup folder for Package Reference Convert tool in Visual Studio 2017
+MigrationBackup/
+
+# Ionide (cross platform F# VS Code tools) working folder
+.ionide/
+
+# Fody - auto-generated XML schema
+FodyWeavers.xsd
+
+.idea/

README.md

@@ -0,0 +1,14 @@
+---
+title: Moe TTS
+emoji: 😊🎙️
+colorFrom: red
+colorTo: pink
+sdk: gradio
+sdk_version: 3.16.1
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: AsakuraMizu/moe-tts
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,320 @@
+import argparse
+import json
+import os
+import re
+import tempfile
+from pathlib import Path
+
+import librosa
+import numpy as np
+import torch
+from torch import no_grad, LongTensor
+import commons
+import utils
+import gradio as gr
+import gradio.utils as gr_utils
+import gradio.processing_utils as gr_processing_utils
+from models import SynthesizerTrn
+from text import text_to_sequence, _clean_text
+from mel_processing import spectrogram_torch
+
+limitation = os.getenv("SYSTEM") == "spaces"  # limit text and audio length in huggingface spaces
+
+audio_postprocess_ori = gr.Audio.postprocess
+
+
+def audio_postprocess(self, y):
+    data = audio_postprocess_ori(self, y)
+    if data is None:
+        return None
+    return gr_processing_utils.encode_url_or_file_to_base64(data["name"])
+
+
+gr.Audio.postprocess = audio_postprocess
+
+
+def get_text(text, hps, is_symbol):
+    text_norm = text_to_sequence(text, hps.symbols, [] if is_symbol else hps.data.text_cleaners)
+    if hps.data.add_blank:
+        text_norm = commons.intersperse(text_norm, 0)
+    text_norm = LongTensor(text_norm)
+    return text_norm
+
+
+def create_tts_fn(model, hps, speaker_ids):
+    def tts_fn(text, speaker, speed, is_symbol):
+        if limitation:
+            text_len = len(re.sub("\[([A-Z]{2})\]", "", text))
+            max_len = 150
+            if is_symbol:
+                max_len *= 3
+            if text_len > max_len:
+                return "Error: Text is too long", None
+
+        speaker_id = speaker_ids[speaker]
+        stn_tst = get_text(text, hps, is_symbol)
+        with no_grad():
+            x_tst = stn_tst.unsqueeze(0).to(device)
+            x_tst_lengths = LongTensor([stn_tst.size(0)]).to(device)
+            sid = LongTensor([speaker_id]).to(device)
+            audio = model.infer(x_tst, x_tst_lengths, sid=sid, noise_scale=.667, noise_scale_w=0.8,
+                                length_scale=1.0 / speed)[0][0, 0].data.cpu().float().numpy()
+        del stn_tst, x_tst, x_tst_lengths, sid
+        return "Success", (hps.data.sampling_rate, audio)
+
+    return tts_fn
+
+
+def create_vc_fn(model, hps, speaker_ids):
+    def vc_fn(original_speaker, target_speaker, input_audio):
+        if input_audio is None:
+            return "You need to upload an audio", None
+        sampling_rate, audio = input_audio
+        duration = audio.shape[0] / sampling_rate
+        if limitation and duration > 30:
+            return "Error: Audio is too long", None
+        original_speaker_id = speaker_ids[original_speaker]
+        target_speaker_id = speaker_ids[target_speaker]
+
+        audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
+        if len(audio.shape) > 1:
+            audio = librosa.to_mono(audio.transpose(1, 0))
+        if sampling_rate != hps.data.sampling_rate:
+            audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=hps.data.sampling_rate)
+        with no_grad():
+            y = torch.FloatTensor(audio)
+            y = y.unsqueeze(0)
+            spec = spectrogram_torch(y, hps.data.filter_length,
+                                     hps.data.sampling_rate, hps.data.hop_length, hps.data.win_length,
+                                     center=False).to(device)
+            spec_lengths = LongTensor([spec.size(-1)]).to(device)
+            sid_src = LongTensor([original_speaker_id]).to(device)
+            sid_tgt = LongTensor([target_speaker_id]).to(device)
+            audio = model.voice_conversion(spec, spec_lengths, sid_src=sid_src, sid_tgt=sid_tgt)[0][
+                0, 0].data.cpu().float().numpy()
+        del y, spec, spec_lengths, sid_src, sid_tgt
+        return "Success", (hps.data.sampling_rate, audio)
+
+    return vc_fn
+
+
+def create_soft_vc_fn(model, hps, speaker_ids):
+    def soft_vc_fn(target_speaker, input_audio1, input_audio2):
+        input_audio = input_audio1
+        if input_audio is None:
+            input_audio = input_audio2
+        if input_audio is None:
+            return "You need to upload an audio", None
+        sampling_rate, audio = input_audio
+        duration = audio.shape[0] / sampling_rate
+        if limitation and duration > 30:
+            return "Error: Audio is too long", None
+        target_speaker_id = speaker_ids[target_speaker]
+
+        audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
+        if len(audio.shape) > 1:
+            audio = librosa.to_mono(audio.transpose(1, 0))
+        if sampling_rate != 16000:
+            audio = librosa.resample(audio, orig_sr=sampling_rate, target_sr=16000)
+        with torch.inference_mode():
+            units = hubert.units(torch.FloatTensor(audio).unsqueeze(0).unsqueeze(0).to(device))
+        with no_grad():
+            unit_lengths = LongTensor([units.size(1)]).to(device)
+            sid = LongTensor([target_speaker_id]).to(device)
+            audio = model.infer(units, unit_lengths, sid=sid, noise_scale=.667,
+                                noise_scale_w=0.8)[0][0, 0].data.cpu().float().numpy()
+        del units, unit_lengths, sid
+        return "Success", (hps.data.sampling_rate, audio)
+
+    return soft_vc_fn
+
+
+def create_to_symbol_fn(hps):
+    def to_symbol_fn(is_symbol_input, input_text, temp_text):
+        return (_clean_text(input_text, hps.data.text_cleaners), input_text) if is_symbol_input \
+            else (temp_text, temp_text)
+
+    return to_symbol_fn
+
+
+download_audio_js = """
+() =>{{
+    let root = document.querySelector("body > gradio-app");
+    if (root.shadowRoot != null)
+        root = root.shadowRoot;
+    let audio = root.querySelector("#{audio_id}").querySelector("audio");
+    if (audio == undefined)
+        return;
+    audio = audio.src;
+    let oA = document.createElement("a");
+    oA.download = Math.floor(Math.random()*100000000)+'.wav';
+    oA.href = audio;
+    document.body.appendChild(oA);
+    oA.click();
+    oA.remove();
+}}
+"""
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--device', type=str, default='cpu')
+    parser.add_argument("--share", action="store_true", default=False, help="share gradio app")
+    args = parser.parse_args()
+
+    device = torch.device(args.device)
+    models_tts = []
+    models_vc = []
+    models_soft_vc = []
+    with open("saved_model/info.json", "r", encoding="utf-8") as f:
+        models_info = json.load(f)
+    for i, info in models_info.items():
+        name = info["title"]
+        author = info["author"]
+        lang = info["lang"]
+        example = info["example"]
+        config_path = f"saved_model/{i}/config.json"
+        model_path = f"saved_model/{i}/model.pth"
+        cover = info["cover"]
+        cover_path = f"saved_model/{i}/{cover}" if cover else None
+        hps = utils.get_hparams_from_file(config_path)
+        model = SynthesizerTrn(
+            len(hps.symbols),
+            hps.data.filter_length // 2 + 1,
+            hps.train.segment_size // hps.data.hop_length,
+            n_speakers=hps.data.n_speakers,
+            **hps.model)
+        utils.load_checkpoint(model_path, model, None)
+        model.eval().to(device)
+        speaker_ids = [sid for sid, name in enumerate(hps.speakers) if name != "None"]
+        speakers = [name for sid, name in enumerate(hps.speakers) if name != "None"]
+
+        t = info["type"]
+        if t == "vits":
+            models_tts.append((name, author, cover_path, speakers, lang, example,
+                               hps.symbols, create_tts_fn(model, hps, speaker_ids),
+                               create_to_symbol_fn(hps)))
+            models_vc.append((name, author, cover_path, speakers, create_vc_fn(model, hps, speaker_ids)))
+        elif t == "soft-vits-vc":
+            models_soft_vc.append((name, author, cover_path, speakers, create_soft_vc_fn(model, hps, speaker_ids)))
+
+    hubert = torch.hub.load("bshall/hubert:main", "hubert_soft", trust_repo=True).to(device)
+
+    app = gr.Blocks()
+
+    with app:
+        gr.Markdown("# Moe TTS And Voice Conversion Using VITS Model\n\n"
+                    "![visitor badge](https://visitor-badge.glitch.me/badge?page_id=skytnt.moegoe)\n\n"
+                    "[Open In Colab]"
+                    "(https://colab.research.google.com/drive/14Pb8lpmwZL-JI5Ub6jpG4sz2-8KS0kbS?usp=sharing)"
+                    " without queue and length limitation.\n\n"
+                    "Feel free to [open discussion](https://huggingface.co/spaces/skytnt/moe-tts/discussions/new) "
+                    "if you want to add your model to this app.")
+        with gr.Tabs():
+            with gr.TabItem("TTS"):
+                with gr.Tabs():
+                    for i, (name, author, cover_path, speakers, lang, example, symbols, tts_fn,
+                            to_symbol_fn) in enumerate(models_tts):
+                        with gr.TabItem(f"model{i}"):
+                            with gr.Column():
+                                cover_markdown = f"![cover](file/{cover_path})\n\n" if cover_path else ""
+                                gr.Markdown(f"## {name}\n\n"
+                                            f"{cover_markdown}"
+                                            f"model author: {author}\n\n"
+                                            f"language: {lang}")
+                                tts_input1 = gr.TextArea(label="Text (150 words limitation)", value=example,
+                                                         elem_id=f"tts-input{i}")
+                                tts_input2 = gr.Dropdown(label="Speaker", choices=speakers,
+                                                         type="index", value=speakers[0])
+                                tts_input3 = gr.Slider(label="Speed", value=1, minimum=0.5, maximum=2, step=0.1)
+                                with gr.Accordion(label="Advanced Options", open=False):
+                                    temp_text_var = gr.Variable()
+                                    symbol_input = gr.Checkbox(value=False, label="Symbol input")
+                                    symbol_list = gr.Dataset(label="Symbol list", components=[tts_input1],
+                                                             samples=[[x] for x in symbols],
+                                                             elem_id=f"symbol-list{i}")
+                                    symbol_list_json = gr.Json(value=symbols, visible=False)
+                                tts_submit = gr.Button("Generate", variant="primary")
+                                tts_output1 = gr.Textbox(label="Output Message")
+                                tts_output2 = gr.Audio(label="Output Audio", elem_id=f"tts-audio{i}")
+                                download = gr.Button("Download Audio")
+                                download.click(None, [], [], _js=download_audio_js.format(audio_id=f"tts-audio{i}"))
+
+                                tts_submit.click(tts_fn, [tts_input1, tts_input2, tts_input3, symbol_input],
+                                                 [tts_output1, tts_output2], api_name=f"tts-model{i}")
+                                symbol_input.change(to_symbol_fn,
+                                                    [symbol_input, tts_input1, temp_text_var],
+                                                    [tts_input1, temp_text_var])
+                                symbol_list.click(None, [symbol_list, symbol_list_json], [],
+                                                  _js=f"""
+                                (i,symbols) => {{
+                                    let root = document.querySelector("body > gradio-app");
+                                    if (root.shadowRoot != null)
+                                        root = root.shadowRoot;
+                                    let text_input = root.querySelector("#tts-input{i}").querySelector("textarea");
+                                    let startPos = text_input.selectionStart;
+                                    let endPos = text_input.selectionEnd;
+                                    let oldTxt = text_input.value;
+                                    let result = oldTxt.substring(0, startPos) + symbols[i] + oldTxt.substring(endPos);
+                                    text_input.value = result;
+                                    let x = window.scrollX, y = window.scrollY;
+                                    text_input.focus();
+                                    text_input.selectionStart = startPos + symbols[i].length;
+                                    text_input.selectionEnd = startPos + symbols[i].length;
+                                    text_input.blur();
+                                    window.scrollTo(x, y);
+                                    return [];
+                                }}""")
+
+            with gr.TabItem("Voice Conversion"):
+                with gr.Tabs():
+                    for i, (name, author, cover_path, speakers, vc_fn) in enumerate(models_vc):
+                        with gr.TabItem(f"model{i}"):
+                            cover_markdown = f"![cover](file/{cover_path})\n\n" if cover_path else ""
+                            gr.Markdown(f"## {name}\n\n"
+                                        f"{cover_markdown}"
+                                        f"model author: {author}")
+                            vc_input1 = gr.Dropdown(label="Original Speaker", choices=speakers, type="index",
+                                                    value=speakers[0])
+                            vc_input2 = gr.Dropdown(label="Target Speaker", choices=speakers, type="index",
+                                                    value=speakers[min(len(speakers) - 1, 1)])
+                            vc_input3 = gr.Audio(label="Input Audio (30s limitation)")
+                            vc_submit = gr.Button("Convert", variant="primary")
+                            vc_output1 = gr.Textbox(label="Output Message")
+                            vc_output2 = gr.Audio(label="Output Audio", elem_id=f"vc-audio{i}")
+                            download = gr.Button("Download Audio")
+                            download.click(None, [], [], _js=download_audio_js.format(audio_id=f"vc-audio{i}"))
+                            vc_submit.click(vc_fn, [vc_input1, vc_input2, vc_input3], [vc_output1, vc_output2], api_name=f"vc-model{i}")
+            with gr.TabItem("Soft Voice Conversion"):
+                with gr.Tabs():
+                    for i, (name, author, cover_path, speakers, soft_vc_fn) in enumerate(models_soft_vc):
+                        with gr.TabItem(f"model{i}"):
+                            cover_markdown = f"![cover](file/{cover_path})\n\n" if cover_path else ""
+                            gr.Markdown(f"## {name}\n\n"
+                                        f"{cover_markdown}"
+                                        f"model author: {author}")
+                            vc_input1 = gr.Dropdown(label="Target Speaker", choices=speakers, type="index",
+                                                    value=speakers[0])
+                            source_tabs = gr.Tabs()
+                            with source_tabs:
+                                with gr.TabItem("microphone"):
+                                    vc_input2 = gr.Audio(label="Input Audio (30s limitation)", source="microphone")
+                                with gr.TabItem("upload"):
+                                    vc_input3 = gr.Audio(label="Input Audio (30s limitation)", source="upload")
+                            vc_submit = gr.Button("Convert", variant="primary")
+                            vc_output1 = gr.Textbox(label="Output Message")
+                            vc_output2 = gr.Audio(label="Output Audio", elem_id=f"svc-audio{i}")
+                            download = gr.Button("Download Audio")
+                            download.click(None, [], [], _js=download_audio_js.format(audio_id=f"svc-audio{i}"))
+                            # clear inputs
+                            source_tabs.set_event_trigger("change", None, [], [vc_input2, vc_input3],
+                                                          js="()=>[null,null]")
+                            vc_submit.click(soft_vc_fn, [vc_input1, vc_input2, vc_input3],
+                                            [vc_output1, vc_output2], api_name=f"svc-model{i}")
+        gr.Markdown(
+            "unofficial demo for \n\n"
+            "- [https://github.com/CjangCjengh/MoeGoe](https://github.com/CjangCjengh/MoeGoe)\n"
+            "- [https://github.com/Francis-Komizu/VITS](https://github.com/Francis-Komizu/VITS)\n"
+            "- [https://github.com/luoyily/MoeTTS](https://github.com/luoyily/MoeTTS)\n"
+            "- [https://github.com/Francis-Komizu/Sovits](https://github.com/Francis-Komizu/Sovits)"
+        )
+    app.queue(concurrency_count=3).launch(share=args.share)

attentions.py

@@ -0,0 +1,300 @@
+import math
+import torch
+from torch import nn
+from torch.nn import functional as F
+
+import commons
+from modules import LayerNorm
+   
+
+class Encoder(nn.Module):
+  def __init__(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., window_size=4, **kwargs):
+    super().__init__()
+    self.hidden_channels = hidden_channels
+    self.filter_channels = filter_channels
+    self.n_heads = n_heads
+    self.n_layers = n_layers
+    self.kernel_size = kernel_size
+    self.p_dropout = p_dropout
+    self.window_size = window_size
+
+    self.drop = nn.Dropout(p_dropout)
+    self.attn_layers = nn.ModuleList()
+    self.norm_layers_1 = nn.ModuleList()
+    self.ffn_layers = nn.ModuleList()
+    self.norm_layers_2 = nn.ModuleList()
+    for i in range(self.n_layers):
+      self.attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout, window_size=window_size))
+      self.norm_layers_1.append(LayerNorm(hidden_channels))
+      self.ffn_layers.append(FFN(hidden_channels, hidden_channels, filter_channels, kernel_size, p_dropout=p_dropout))
+      self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+  def forward(self, x, x_mask):
+    attn_mask = x_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+    x = x * x_mask
+    for i in range(self.n_layers):
+      y = self.attn_layers[i](x, x, attn_mask)
+      y = self.drop(y)
+      x = self.norm_layers_1[i](x + y)
+
+      y = self.ffn_layers[i](x, x_mask)
+      y = self.drop(y)
+      x = self.norm_layers_2[i](x + y)
+    x = x * x_mask
+    return x
+
+
+class Decoder(nn.Module):
+  def __init__(self, hidden_channels, filter_channels, n_heads, n_layers, kernel_size=1, p_dropout=0., proximal_bias=False, proximal_init=True, **kwargs):
+    super().__init__()
+    self.hidden_channels = hidden_channels
+    self.filter_channels = filter_channels
+    self.n_heads = n_heads
+    self.n_layers = n_layers
+    self.kernel_size = kernel_size
+    self.p_dropout = p_dropout
+    self.proximal_bias = proximal_bias
+    self.proximal_init = proximal_init
+
+    self.drop = nn.Dropout(p_dropout)
+    self.self_attn_layers = nn.ModuleList()
+    self.norm_layers_0 = nn.ModuleList()
+    self.encdec_attn_layers = nn.ModuleList()
+    self.norm_layers_1 = nn.ModuleList()
+    self.ffn_layers = nn.ModuleList()
+    self.norm_layers_2 = nn.ModuleList()
+    for i in range(self.n_layers):
+      self.self_attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout, proximal_bias=proximal_bias, proximal_init=proximal_init))
+      self.norm_layers_0.append(LayerNorm(hidden_channels))
+      self.encdec_attn_layers.append(MultiHeadAttention(hidden_channels, hidden_channels, n_heads, p_dropout=p_dropout))
+      self.norm_layers_1.append(LayerNorm(hidden_channels))
+      self.ffn_layers.append(FFN(hidden_channels, hidden_channels, filter_channels, kernel_size, p_dropout=p_dropout, causal=True))
+      self.norm_layers_2.append(LayerNorm(hidden_channels))
+
+  def forward(self, x, x_mask, h, h_mask):
+    """
+    x: decoder input
+    h: encoder output
+    """
+    self_attn_mask = commons.subsequent_mask(x_mask.size(2)).to(device=x.device, dtype=x.dtype)
+    encdec_attn_mask = h_mask.unsqueeze(2) * x_mask.unsqueeze(-1)
+    x = x * x_mask
+    for i in range(self.n_layers):
+      y = self.self_attn_layers[i](x, x, self_attn_mask)
+      y = self.drop(y)
+      x = self.norm_layers_0[i](x + y)
+
+      y = self.encdec_attn_layers[i](x, h, encdec_attn_mask)
+      y = self.drop(y)
+      x = self.norm_layers_1[i](x + y)
+      
+      y = self.ffn_layers[i](x, x_mask)
+      y = self.drop(y)
+      x = self.norm_layers_2[i](x + y)
+    x = x * x_mask
+    return x
+
+
+class MultiHeadAttention(nn.Module):
+  def __init__(self, channels, out_channels, n_heads, p_dropout=0., window_size=None, heads_share=True, block_length=None, proximal_bias=False, proximal_init=False):
+    super().__init__()
+    assert channels % n_heads == 0
+
+    self.channels = channels
+    self.out_channels = out_channels
+    self.n_heads = n_heads
+    self.p_dropout = p_dropout
+    self.window_size = window_size
+    self.heads_share = heads_share
+    self.block_length = block_length
+    self.proximal_bias = proximal_bias
+    self.proximal_init = proximal_init
+    self.attn = None
+
+    self.k_channels = channels // n_heads
+    self.conv_q = nn.Conv1d(channels, channels, 1)
+    self.conv_k = nn.Conv1d(channels, channels, 1)
+    self.conv_v = nn.Conv1d(channels, channels, 1)
+    self.conv_o = nn.Conv1d(channels, out_channels, 1)
+    self.drop = nn.Dropout(p_dropout)
+
+    if window_size is not None:
+      n_heads_rel = 1 if heads_share else n_heads
+      rel_stddev = self.k_channels**-0.5
+      self.emb_rel_k = nn.Parameter(torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) * rel_stddev)
+      self.emb_rel_v = nn.Parameter(torch.randn(n_heads_rel, window_size * 2 + 1, self.k_channels) * rel_stddev)
+
+    nn.init.xavier_uniform_(self.conv_q.weight)
+    nn.init.xavier_uniform_(self.conv_k.weight)
+    nn.init.xavier_uniform_(self.conv_v.weight)
+    if proximal_init:
+      with torch.no_grad():
+        self.conv_k.weight.copy_(self.conv_q.weight)
+        self.conv_k.bias.copy_(self.conv_q.bias)
+      
+  def forward(self, x, c, attn_mask=None):
+    q = self.conv_q(x)
+    k = self.conv_k(c)
+    v = self.conv_v(c)
+    
+    x, self.attn = self.attention(q, k, v, mask=attn_mask)
+
+    x = self.conv_o(x)
+    return x
+
+  def attention(self, query, key, value, mask=None):
+    # reshape [b, d, t] -> [b, n_h, t, d_k]
+    b, d, t_s, t_t = (*key.size(), query.size(2))
+    query = query.view(b, self.n_heads, self.k_channels, t_t).transpose(2, 3)
+    key = key.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+    value = value.view(b, self.n_heads, self.k_channels, t_s).transpose(2, 3)
+
+    scores = torch.matmul(query / math.sqrt(self.k_channels), key.transpose(-2, -1))
+    if self.window_size is not None:
+      assert t_s == t_t, "Relative attention is only available for self-attention."
+      key_relative_embeddings = self._get_relative_embeddings(self.emb_rel_k, t_s)
+      rel_logits = self._matmul_with_relative_keys(query /math.sqrt(self.k_channels), key_relative_embeddings)
+      scores_local = self._relative_position_to_absolute_position(rel_logits)
+      scores = scores + scores_local
+    if self.proximal_bias:
+      assert t_s == t_t, "Proximal bias is only available for self-attention."
+      scores = scores + self._attention_bias_proximal(t_s).to(device=scores.device, dtype=scores.dtype)
+    if mask is not None:
+      scores = scores.masked_fill(mask == 0, -1e4)
+      if self.block_length is not None:
+        assert t_s == t_t, "Local attention is only available for self-attention."
+        block_mask = torch.ones_like(scores).triu(-self.block_length).tril(self.block_length)
+        scores = scores.masked_fill(block_mask == 0, -1e4)
+    p_attn = F.softmax(scores, dim=-1) # [b, n_h, t_t, t_s]
+    p_attn = self.drop(p_attn)
+    output = torch.matmul(p_attn, value)
+    if self.window_size is not None:
+      relative_weights = self._absolute_position_to_relative_position(p_attn)
+      value_relative_embeddings = self._get_relative_embeddings(self.emb_rel_v, t_s)
+      output = output + self._matmul_with_relative_values(relative_weights, value_relative_embeddings)
+    output = output.transpose(2, 3).contiguous().view(b, d, t_t) # [b, n_h, t_t, d_k] -> [b, d, t_t]
+    return output, p_attn
+
+  def _matmul_with_relative_values(self, x, y):
+    """
+    x: [b, h, l, m]
+    y: [h or 1, m, d]
+    ret: [b, h, l, d]
+    """
+    ret = torch.matmul(x, y.unsqueeze(0))
+    return ret
+
+  def _matmul_with_relative_keys(self, x, y):
+    """
+    x: [b, h, l, d]
+    y: [h or 1, m, d]
+    ret: [b, h, l, m]
+    """
+    ret = torch.matmul(x, y.unsqueeze(0).transpose(-2, -1))
+    return ret
+
+  def _get_relative_embeddings(self, relative_embeddings, length):
+    max_relative_position = 2 * self.window_size + 1
+    # Pad first before slice to avoid using cond ops.
+    pad_length = max(length - (self.window_size + 1), 0)
+    slice_start_position = max((self.window_size + 1) - length, 0)
+    slice_end_position = slice_start_position + 2 * length - 1
+    if pad_length > 0:
+      padded_relative_embeddings = F.pad(
+          relative_embeddings,
+          commons.convert_pad_shape([[0, 0], [pad_length, pad_length], [0, 0]]))
+    else:
+      padded_relative_embeddings = relative_embeddings
+    used_relative_embeddings = padded_relative_embeddings[:,slice_start_position:slice_end_position]
+    return used_relative_embeddings
+
+  def _relative_position_to_absolute_position(self, x):
+    """
+    x: [b, h, l, 2*l-1]
+    ret: [b, h, l, l]
+    """
+    batch, heads, length, _ = x.size()
+    # Concat columns of pad to shift from relative to absolute indexing.
+    x = F.pad(x, commons.convert_pad_shape([[0,0],[0,0],[0,0],[0,1]]))
+
+    # Concat extra elements so to add up to shape (len+1, 2*len-1).
+    x_flat = x.view([batch, heads, length * 2 * length])
+    x_flat = F.pad(x_flat, commons.convert_pad_shape([[0,0],[0,0],[0,length-1]]))
+
+    # Reshape and slice out the padded elements.
+    x_final = x_flat.view([batch, heads, length+1, 2*length-1])[:, :, :length, length-1:]
+    return x_final
+
+  def _absolute_position_to_relative_position(self, x):
+    """
+    x: [b, h, l, l]
+    ret: [b, h, l, 2*l-1]
+    """
+    batch, heads, length, _ = x.size()
+    # padd along column
+    x = F.pad(x, commons.convert_pad_shape([[0, 0], [0, 0], [0, 0], [0, length-1]]))
+    x_flat = x.view([batch, heads, length**2 + length*(length -1)])
+    # add 0's in the beginning that will skew the elements after reshape
+    x_flat = F.pad(x_flat, commons.convert_pad_shape([[0, 0], [0, 0], [length, 0]]))
+    x_final = x_flat.view([batch, heads, length, 2*length])[:,:,:,1:]
+    return x_final
+
+  def _attention_bias_proximal(self, length):
+    """Bias for self-attention to encourage attention to close positions.
+    Args:
+      length: an integer scalar.
+    Returns:
+      a Tensor with shape [1, 1, length, length]
+    """
+    r = torch.arange(length, dtype=torch.float32)
+    diff = torch.unsqueeze(r, 0) - torch.unsqueeze(r, 1)
+    return torch.unsqueeze(torch.unsqueeze(-torch.log1p(torch.abs(diff)), 0), 0)
+
+
+class FFN(nn.Module):
+  def __init__(self, in_channels, out_channels, filter_channels, kernel_size, p_dropout=0., activation=None, causal=False):
+    super().__init__()
+    self.in_channels = in_channels
+    self.out_channels = out_channels
+    self.filter_channels = filter_channels
+    self.kernel_size = kernel_size
+    self.p_dropout = p_dropout
+    self.activation = activation
+    self.causal = causal
+
+    if causal:
+      self.padding = self._causal_padding
+    else:
+      self.padding = self._same_padding
+
+    self.conv_1 = nn.Conv1d(in_channels, filter_channels, kernel_size)
+    self.conv_2 = nn.Conv1d(filter_channels, out_channels, kernel_size)
+    self.drop = nn.Dropout(p_dropout)
+
+  def forward(self, x, x_mask):
+    x = self.conv_1(self.padding(x * x_mask))
+    if self.activation == "gelu":
+      x = x * torch.sigmoid(1.702 * x)
+    else:
+      x = torch.relu(x)
+    x = self.drop(x)
+    x = self.conv_2(self.padding(x * x_mask))
+    return x * x_mask
+  
+  def _causal_padding(self, x):
+    if self.kernel_size == 1:
+      return x
+    pad_l = self.kernel_size - 1
+    pad_r = 0
+    padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+    x = F.pad(x, commons.convert_pad_shape(padding))
+    return x
+
+  def _same_padding(self, x):
+    if self.kernel_size == 1:
+      return x
+    pad_l = (self.kernel_size - 1) // 2
+    pad_r = self.kernel_size // 2
+    padding = [[0, 0], [0, 0], [pad_l, pad_r]]
+    x = F.pad(x, commons.convert_pad_shape(padding))
+    return x

chinese_dialect_lexicons/changzhou.json

@@ -0,0 +1,23 @@
+{
+  "name": "Changzhou dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "changzhou.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "changzhou.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/changzhou.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db4ec02be9812e804291a88f9a984f544e221ed472f682bba8da5ecbefbabd8c
+size 96119

chinese_dialect_lexicons/cixi.json

@@ -0,0 +1,23 @@
+{
+  "name": "Cixi dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "cixi.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "cixi.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/cixi.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8113aca87c4728c66cfa6c7b5adfbb596a2930df9b7c6187c6a227ff2de87f00
+size 98015

chinese_dialect_lexicons/fuyang.json

@@ -0,0 +1,23 @@
+{
+  "name": "Fuyang dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "fuyang.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "fuyang.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/fuyang.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98e1fbec75e090550cf131de226a1d867c7896b51170f8d7d21f9101297f4c08
+size 83664

chinese_dialect_lexicons/hangzhou.json

@@ -0,0 +1,19 @@
+{
+  "name": "Hangzhounese to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "hangzhou.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "hangzhou.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/hangzhou.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7a9eb5fbd3b8c91745dbb2734f2700b75a47c3821e381566afc567d7da4d9d5
+size 427268

chinese_dialect_lexicons/jiading.json

@@ -0,0 +1,23 @@
+{
+  "name": "Jiading dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "jiading.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "jiading.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/jiading.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f3ac33214e65e7223e8c561bc12ec90a2d87db3cf8d20e87a30bbd8eb788187
+size 111144

chinese_dialect_lexicons/jiashan.json

@@ -0,0 +1,23 @@
+{
+  "name": "Jiashan dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "jiashan.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "jiashan.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/jiashan.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6310729b85976b6e6407b4f66ad13a3ad7a51a42f3c05c98e294bcbb3159456c
+size 71716

chinese_dialect_lexicons/jingjiang.json

@@ -0,0 +1,23 @@
+{
+  "name": "Jingjiang dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "jingjiang.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "jingjiang.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/jingjiang.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154d9cac032a3284a6aa175689a5805f068f6896429009a7d94d41616694131f
+size 86093

chinese_dialect_lexicons/jyutjyu.json

@@ -0,0 +1,19 @@
+{
+  "name": "Cantonese to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "jyutjyu.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "jyutjyu.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/jyutjyu.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea11bfe51b184b3f000d20ab49757979b216219203839d2b2e3c1f990a13fa5
+size 2432991

chinese_dialect_lexicons/linping.json

@@ -0,0 +1,23 @@
+{
+  "name": "Linping dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "linping.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "linping.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/linping.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fcd3b53e5aa6cd64419835c14769d53cc230e229c0fbd20efb65c46e07b712b
+size 65351

chinese_dialect_lexicons/ningbo.json

@@ -0,0 +1,19 @@
+{
+  "name": "Ningbonese to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "ningbo.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "ningbo.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/ningbo.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5876b000f611ea52bf18cda5bcbdd0cfcc55e1c09774d9a24e3b5c7d90002435
+size 386414

chinese_dialect_lexicons/pinghu.json

@@ -0,0 +1,23 @@
+{
+  "name": "Pinghu dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "pinghu.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "pinghu.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/pinghu.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b0e0dad8cddb0e2cb23899d4a2f97f2c0b369d5ff369076c5cdb7bd4528e4f
+size 69420

chinese_dialect_lexicons/ruao.json

@@ -0,0 +1,23 @@
+{
+  "name": "Ruao dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "ruao.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "ruao.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/ruao.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:259a42ad761233f7d6ca6eec39268e27a65b2ded025f2b7725501cf5e3e02d8a
+size 58841

chinese_dialect_lexicons/sanmen.json

@@ -0,0 +1,23 @@
+{
+  "name": "Sanmen dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "sanmen.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "sanmen.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/sanmen.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa70a920b6805e279ed15246026b70dbeb2a8329ad585fbae8cfdf45e7489a9
+size 80210

chinese_dialect_lexicons/shaoxing.json

@@ -0,0 +1,23 @@
+{
+  "name": "Shaoxing dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "shaoxing.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "shaoxing.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/shaoxing.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a347aa25bf435803727b4194cf34de4de3e61f03427ee21043a711cdb0b9d940
+size 113108

chinese_dialect_lexicons/suichang.json

@@ -0,0 +1,23 @@
+{
+  "name": "Suichang dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "suichang.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "suichang.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/suichang.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8062749ff70db65d469d91bd92375607f8648a138b896e58cf7c28edb8f970e
+size 81004

chinese_dialect_lexicons/suzhou.json

@@ -0,0 +1,19 @@
+{
+  "name": "Suzhounese to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "suzhou.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "suzhou.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/suzhou.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8815595a248135874329e7f34662dd243a266be3e8375e8409f95da95d6d540
+size 506184

chinese_dialect_lexicons/tiantai.json

@@ -0,0 +1,23 @@
+{
+  "name": "Tiantai dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "tiantai.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "tiantai.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/tiantai.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339e0ba454444dbf8fbe75de6f49769d11dfe2f2f5ba7dea74ba20fba5d6d343
+size 120951

chinese_dialect_lexicons/tongxiang.json

@@ -0,0 +1,23 @@
+{
+  "name": "Tongxiang dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "tongxiang.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "tongxiang.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/tongxiang.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7432d85588eb8ba34e7baea9f26af8d332572037ff7d41a6730f96c02e5fd063
+size 137499

chinese_dialect_lexicons/wenzhou.json

@@ -0,0 +1,23 @@
+{
+  "name": "Wenzhou dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "wenzhou.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "wenzhou.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/wenzhou.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed05c0c615a38f55a139a73bcc3960897d8cd567c9482a0a06b272eb0b46aa05
+size 83121

chinese_dialect_lexicons/wuxi.json

@@ -0,0 +1,19 @@
+{
+  "name": "Wuxinese to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "wuxi.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "wuxi.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/wuxi.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64f27ffaa75e542e4464e53c4acf94607be1526a90922ac8b28870104aaebdff
+size 358666

chinese_dialect_lexicons/xiaoshan.json

@@ -0,0 +1,23 @@
+{
+  "name": "Xiaoshan dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "xiaoshan.ocd2"
+    }
+  },
+  "conversion_chain": [
+    {
+      "dict": {
+        "type": "group",
+        "dicts": [
+          {
+            "type": "ocd2",
+            "file": "xiaoshan.ocd2"
+          }
+        ]
+      }
+    }
+  ]
+}

chinese_dialect_lexicons/xiaoshan.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:651bd314c5e57312eeee537037f6c6e56a12ef446216264aad70bf68bf6a283d
+size 77119

chinese_dialect_lexicons/xiashi.json

@@ -0,0 +1,19 @@
+{
+  "name": "Xiashi dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "xiashi.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "xiashi.ocd2"
+      }] 
+    }
+  }]
+}

chinese_dialect_lexicons/xiashi.ocd2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bc638633b82e196776a3adfc621c854d0da923b7cff6e7d0c9576723cdc03cd
+size 70314

chinese_dialect_lexicons/yixing.json

@@ -0,0 +1,19 @@
+{
+  "name": "Yixing dialect to IPA",
+  "segmentation": {
+    "type": "mmseg",
+    "dict": {
+      "type": "ocd2",
+      "file": "yixing.ocd2"
+    }
+  },
+  "conversion_chain": [{
+    "dict": {
+      "type": "group",
+      "dicts": [{
+        "type": "ocd2",
+        "file": "yixing.ocd2"
+      }] 
+    }
+  }]
+}