azalea/VITS-fast-fine-tuning
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

upload files

Browse Source
This commit is contained in:
Plachta
2023-02-13 14:17:54 +08:00
parent 23774894a5
commit db8b5f801c
12 changed files with 393 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.idea/.gitignore
Generated
+3
View File
@@ -0,0 +1,3 @@
# Default ignored files
/shelf/
/workspace.xml
.idea/VITS_voice_conversion.iml
Generated
+12
View File
@@ -0,0 +1,12 @@
<?xml version="1.0" encoding="UTF-8"?>
<module type="PYTHON_MODULE" version="4">
<component name="NewModuleRootManager">
<content url="file://$MODULE_DIR$" />
<orderEntry type="jdk" jdkName="Python 3.7 (VITS)" jdkType="Python SDK" />
<orderEntry type="sourceFolder" forTests="false" />
</component>
<component name="PyDocumentationSettings">
<option name="format" value="PLAIN" />
<option name="myDocStringFormat" value="Plain" />
</component>
</module>
.idea/inspectionProfiles/Project_Default.xml
Generated
+154
View File
@@ -0,0 +1,154 @@
<component name="InspectionProjectProfileManager">
<profile version="1.0">
<option name="myName" value="Project Default" />
<inspection_tool class="PyPackageRequirementsInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredPackages">
<value>
<list size="132">
<item index="0" class="java.lang.String" itemvalue="ccxt" />
<item index="1" class="java.lang.String" itemvalue="lz4" />
<item index="2" class="java.lang.String" itemvalue="pre-commit" />
<item index="3" class="java.lang.String" itemvalue="elegantrl" />
<item index="4" class="java.lang.String" itemvalue="setuptools" />
<item index="5" class="java.lang.String" itemvalue="ray" />
<item index="6" class="java.lang.String" itemvalue="gputil" />
<item index="7" class="java.lang.String" itemvalue="google-pasta" />
<item index="8" class="java.lang.String" itemvalue="tensorflow-estimator" />
<item index="9" class="java.lang.String" itemvalue="scikit-learn" />
<item index="10" class="java.lang.String" itemvalue="tabulate" />
<item index="11" class="java.lang.String" itemvalue="multitasking" />
<item index="12" class="java.lang.String" itemvalue="pickleshare" />
<item index="13" class="java.lang.String" itemvalue="pyasn1-modules" />
<item index="14" class="java.lang.String" itemvalue="ipython-genutils" />
<item index="15" class="java.lang.String" itemvalue="Pygments" />
<item index="16" class="java.lang.String" itemvalue="mccabe" />
<item index="17" class="java.lang.String" itemvalue="astunparse" />
<item index="18" class="java.lang.String" itemvalue="lxml" />
<item index="19" class="java.lang.String" itemvalue="Werkzeug" />
<item index="20" class="java.lang.String" itemvalue="tensorboard-data-server" />
<item index="21" class="java.lang.String" itemvalue="jupyter-client" />
<item index="22" class="java.lang.String" itemvalue="pexpect" />
<item index="23" class="java.lang.String" itemvalue="click" />
<item index="24" class="java.lang.String" itemvalue="ipykernel" />
<item index="25" class="java.lang.String" itemvalue="pandas-datareader" />
<item index="26" class="java.lang.String" itemvalue="psutil" />
<item index="27" class="java.lang.String" itemvalue="jedi" />
<item index="28" class="java.lang.String" itemvalue="regex" />
<item index="29" class="java.lang.String" itemvalue="tensorboard" />
<item index="30" class="java.lang.String" itemvalue="platformdirs" />
<item index="31" class="java.lang.String" itemvalue="matplotlib" />
<item index="32" class="java.lang.String" itemvalue="idna" />
<item index="33" class="java.lang.String" itemvalue="rsa" />
<item index="34" class="java.lang.String" itemvalue="decorator" />
<item index="35" class="java.lang.String" itemvalue="numpy" />
<item index="36" class="java.lang.String" itemvalue="pyasn1" />
<item index="37" class="java.lang.String" itemvalue="requests" />
<item index="38" class="java.lang.String" itemvalue="tensorflow" />
<item index="39" class="java.lang.String" itemvalue="tensorboard-plugin-wit" />
<item index="40" class="java.lang.String" itemvalue="Deprecated" />
<item index="41" class="java.lang.String" itemvalue="nest-asyncio" />
<item index="42" class="java.lang.String" itemvalue="prompt-toolkit" />
<item index="43" class="java.lang.String" itemvalue="keras-tuner" />
<item index="44" class="java.lang.String" itemvalue="scipy" />
<item index="45" class="java.lang.String" itemvalue="dataclasses" />
<item index="46" class="java.lang.String" itemvalue="tornado" />
<item index="47" class="java.lang.String" itemvalue="google-auth-oauthlib" />
<item index="48" class="java.lang.String" itemvalue="black" />
<item index="49" class="java.lang.String" itemvalue="toml" />
<item index="50" class="java.lang.String" itemvalue="Quandl" />
<item index="51" class="java.lang.String" itemvalue="pandas" />
<item index="52" class="java.lang.String" itemvalue="termcolor" />
<item index="53" class="java.lang.String" itemvalue="pylint" />
<item index="54" class="java.lang.String" itemvalue="typing_extensions" />
<item index="55" class="java.lang.String" itemvalue="cachetools" />
<item index="56" class="java.lang.String" itemvalue="debugpy" />
<item index="57" class="java.lang.String" itemvalue="isort" />
<item index="58" class="java.lang.String" itemvalue="pytz" />
<item index="59" class="java.lang.String" itemvalue="inflection" />
<item index="60" class="java.lang.String" itemvalue="Pillow" />
<item index="61" class="java.lang.String" itemvalue="traitlets" />
<item index="62" class="java.lang.String" itemvalue="absl-py" />
<item index="63" class="java.lang.String" itemvalue="protobuf" />
<item index="64" class="java.lang.String" itemvalue="joblib" />
<item index="65" class="java.lang.String" itemvalue="threadpoolctl" />
<item index="66" class="java.lang.String" itemvalue="opt-einsum" />
<item index="67" class="java.lang.String" itemvalue="python-dateutil" />
<item index="68" class="java.lang.String" itemvalue="gpflow" />
<item index="69" class="java.lang.String" itemvalue="astroid" />
<item index="70" class="java.lang.String" itemvalue="cycler" />
<item index="71" class="java.lang.String" itemvalue="gast" />
<item index="72" class="java.lang.String" itemvalue="kt-legacy" />
<item index="73" class="java.lang.String" itemvalue="appdirs" />
<item index="74" class="java.lang.String" itemvalue="tensorflow-probability" />
<item index="75" class="java.lang.String" itemvalue="pip" />
<item index="76" class="java.lang.String" itemvalue="pyzmq" />
<item index="77" class="java.lang.String" itemvalue="certifi" />
<item index="78" class="java.lang.String" itemvalue="oauthlib" />
<item index="79" class="java.lang.String" itemvalue="pyparsing" />
<item index="80" class="java.lang.String" itemvalue="Markdown" />
<item index="81" class="java.lang.String" itemvalue="h5py" />
<item index="82" class="java.lang.String" itemvalue="wrapt" />
<item index="83" class="java.lang.String" itemvalue="kiwisolver" />
<item index="84" class="java.lang.String" itemvalue="empyrical" />
<item index="85" class="java.lang.String" itemvalue="backcall" />
<item index="86" class="java.lang.String" itemvalue="charset-normalizer" />
<item index="87" class="java.lang.String" itemvalue="multipledispatch" />
<item index="88" class="java.lang.String" itemvalue="pathspec" />
<item index="89" class="java.lang.String" itemvalue="jupyter-core" />
<item index="90" class="java.lang.String" itemvalue="matplotlib-inline" />
<item index="91" class="java.lang.String" itemvalue="ptyprocess" />
<item index="92" class="java.lang.String" itemvalue="more-itertools" />
<item index="93" class="java.lang.String" itemvalue="mypy-extensions" />
<item index="94" class="java.lang.String" itemvalue="cloudpickle" />
<item index="95" class="java.lang.String" itemvalue="wcwidth" />
<item index="96" class="java.lang.String" itemvalue="requests-oauthlib" />
<item index="97" class="java.lang.String" itemvalue="Keras-Preprocessing" />
<item index="98" class="java.lang.String" itemvalue="yfinance" />
<item index="99" class="java.lang.String" itemvalue="tomli" />
<item index="100" class="java.lang.String" itemvalue="urllib3" />
<item index="101" class="java.lang.String" itemvalue="six" />
<item index="102" class="java.lang.String" itemvalue="parso" />
<item index="103" class="java.lang.String" itemvalue="wheel" />
<item index="104" class="java.lang.String" itemvalue="ipython" />
<item index="105" class="java.lang.String" itemvalue="packaging" />
<item index="106" class="java.lang.String" itemvalue="lazy-object-proxy" />
<item index="107" class="java.lang.String" itemvalue="grpcio" />
<item index="108" class="java.lang.String" itemvalue="dm-tree" />
<item index="109" class="java.lang.String" itemvalue="google-auth" />
<item index="110" class="java.lang.String" itemvalue="seaborn" />
<item index="111" class="java.lang.String" itemvalue="thop" />
<item index="112" class="java.lang.String" itemvalue="torch" />
<item index="113" class="java.lang.String" itemvalue="torchvision" />
<item index="114" class="java.lang.String" itemvalue="d2l" />
<item index="115" class="java.lang.String" itemvalue="keyboard" />
<item index="116" class="java.lang.String" itemvalue="transformers" />
<item index="117" class="java.lang.String" itemvalue="phonemizer" />
<item index="118" class="java.lang.String" itemvalue="Unidecode" />
<item index="119" class="java.lang.String" itemvalue="nltk" />
<item index="120" class="java.lang.String" itemvalue="pinecone-client" />
<item index="121" class="java.lang.String" itemvalue="sentence-transformers" />
<item index="122" class="java.lang.String" itemvalue="whisper" />
<item index="123" class="java.lang.String" itemvalue="datasets" />
<item index="124" class="java.lang.String" itemvalue="pyaudio" />
<item index="125" class="java.lang.String" itemvalue="torchsummary" />
<item index="126" class="java.lang.String" itemvalue="openjtalk" />
<item index="127" class="java.lang.String" itemvalue="hydra-core" />
<item index="128" class="java.lang.String" itemvalue="museval" />
<item index="129" class="java.lang.String" itemvalue="mypy" />
<item index="130" class="java.lang.String" itemvalue="hydra-colorlog" />
<item index="131" class="java.lang.String" itemvalue="flake8" />
</list>
</value>
</option>
</inspection_tool>
<inspection_tool class="PyUnresolvedReferencesInspection" enabled="true" level="WARNING" enabled_by_default="true">
<option name="ignoredIdentifiers">
<list>
<option value="sentiment_classification.model_predictions.audio_path" />
<option value="sentiment_classification.model_predictions.sample_rate" />
<option value="sentiment_classification.model_predictions.num_samples" />
</list>
</option>
</inspection_tool>
</profile>
</component>
.idea/inspectionProfiles/profiles_settings.xml
Generated
+6
View File
@@ -0,0 +1,6 @@
<component name="InspectionProjectProfileManager">
<settings>
<option name="USE_PROJECT_PROFILE" value="false" />
<version value="1.0" />
</settings>
</component>
.idea/misc.xml
Generated
+4
View File
@@ -0,0 +1,4 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectRootManager" version="2" project-jdk-name="Python 3.7 (VITS)" project-jdk-type="Python SDK" />
</project>
.idea/modules.xml
Generated
+8
View File
@@ -0,0 +1,8 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="ProjectModuleManager">
<modules>
<module fileurl="file://$PROJECT_DIR$/.idea/VITS_voice_conversion.iml" filepath="$PROJECT_DIR$/.idea/VITS_voice_conversion.iml" />
</modules>
</component>
</project>
.idea/vcs.xml
Generated
+6
View File
@@ -0,0 +1,6 @@
<?xml version="1.0" encoding="UTF-8"?>
<project version="4">
<component name="VcsDirectoryMappings">
<mapping directory="$PROJECT_DIR$" vcs="Git" />
</component>
</project>
.ipynb_checkpoints/VITS_vc_ft-checkpoint.ipynb
+6
View File
@@ -0,0 +1,6 @@
{
"cells": [],
"metadata": {},
"nbformat": 4,
"nbformat_minor": 5
}
VITS_vc_ft.ipynb
+33
View File
@@ -0,0 +1,33 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "2c6bd36c",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.0"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
user_voice/user_voice.txt
+45
View File
@@ -0,0 +1,45 @@
0.wav|999|[ZH]所以，人的内在拥有对于人的幸福才是最关键的。[ZH]
1.wav|999|[ZH]正因为在大多数情形下人的自身内在相当贫乏，[ZH]
2.wav|999|[ZH]所以，那些再也用不着与生活的匮乏作斗争的人，[ZH]
3.wav|999|[ZH]他们之中的大多数从根本上还是感觉闷闷不乐。[ZH]
4.wav|999|[ZH]情形就跟那些还在生活的困苦中搏斗的人一般无异。[ZH]
5.wav|999|[ZH]他们内在空虚、感觉意识呆滞、思想匮乏，[ZH]
6.wav|999|[ZH]这些就驱使他们投入社交人群中。[ZH]
7.wav|999|[ZH]组成那些社交圈子的人也正是他们这一类的人。[ZH]
8.wav|999|[ZH]“因为相同羽毛的鸟聚在一块”。[ZH]
9.wav|999|[ZH]他们聚在一块追逐消遣、娱乐。[ZH]
10.wav|999|[ZH]他们以放纵感官的欢娱、极尽声色的享受开始，[ZH]
11.wav|999|[ZH]以荒唐、无度而告终。[ZH]
12.wav|999|[ZH]众多刚刚踏入生活的纨绔子弟穷奢极欲，[ZH]
13.wav|999|[ZH]在令人难以置信的极短时间内就把大部分家财挥霍殆尽。[ZH]
14.wav|999|[ZH]这种做派，其根源确实不是别的，正是无聊[ZH]
18.wav|999|[ZH]它源自上述的精神贫乏和空虚。[ZH]
16.wav|999|[ZH]一个外在富有、但内在贫乏的富家子弟来到这个世界，[ZH]
17.wav|999|[ZH]会徒劳地用外在的财富去补偿内在的不足；[ZH]
18.wav|999|[ZH]他渴望从外部得到一切，[ZH]
19.wav|999|[ZH]这情形就好比试图以少女的汗水去强健自己体魄的老朽之人。[ZH]
20.wav|999|[ZH]人自身内在的贫乏由此导致了外在财富的贫乏。[ZH]
21.wav|999|[ZH]至于另外两项人生好处的重要性，[ZH]
22.wav|999|[ZH]不需要我特别强调。[ZH]
23.wav|999|[ZH]财产的价值在当今是人所公认的，[ZH]
24.wav|999|[ZH]用不着为其宣传介绍。[ZH]
25.wav|999|[ZH]比起第二项的好处，[ZH]
26.wav|999|[ZH]第三项的好处具有一种相当飘渺的成分，[ZH]
27.wav|999|[ZH]因为名誉、名望、地位等[ZH]
28.wav|999|[ZH]全由他人的意见构成。[ZH]
29.wav|999|[ZH]每人都可以争取得到名誉，[ZH]
30.wav|999|[ZH]亦即清白的名声；[ZH]
31.wav|999|[ZH]但社会地位，则只有月盼国家政府的人才能染指；[ZH]
32.wav|999|[ZH]至于显赫的名望就只有极少数人才会得到。[ZH]
33.wav|999|[ZH]在所有这些当中，[ZH]
34.wav|999|[ZH]名誉是弥足珍贵的；[ZH]
35.wav|999|[ZH]显赫的名望则是人所希望得到的价值至昂的东西，[ZH]
36.wav|999|[ZH]那是天之骄子才能得到的金羊毛。[ZH]
37.wav|999|[ZH]另一方面，[ZH]
38.wav|999|[ZH]只有傻瓜才会把社会地位放置在财产之前。[ZH]
39.wav|999|[ZH]另外，人拥有的财产、物品和名誉、声望，[ZH]
40.wav|999|[ZH]是处于一种所谓的互为影响、促进的关系。[ZH]
41.wav|999|[ZH]彼得尼斯说过：“一个人所拥有的财产决定了这个人在他人眼中的价值”。[ZH]
42.wav|999|[ZH]如果这句话是正确的话，[ZH]
43.wav|999|[ZH]那么，反过来，他人对自己的良好评价，[ZH]
44.wav|999|[ZH]能以各种形式帮助自己获取财产。[ZH]
user_voice/user_voice.txt.cleaned
+45
View File
@@ -0,0 +1,45 @@
0.wav|999|swo↓↑i↓↑, ɹ`ən↑ t⁼ə neɪ↓ts⁼aɪ↓ jʊŋ→joʊ↓↑ t⁼weɪ↓ɥ↑ ɹ`ən↑ t⁼ə ʃiŋ↓fu↑ tsʰaɪ↑ s`ɹ`↓ ts⁼weɪ↓ k⁼wan→tʃ⁼jɛn↓ t⁼ə.
1.wav|999|ts`⁼əŋ↓ in→weɪ↓ ts⁼aɪ↓ t⁼a↓t⁼wo→s`u↓ tʃʰiŋ↑ʃiŋ↑ ʃja↓ɹ`ən↑ t⁼ə ts⁼ɹ↓s`ən→ neɪ↓ts⁼aɪ↓ ʃiɑŋ→t⁼ɑŋ→ pʰin↑fa↑,
2.wav|999|swo↓↑i↓↑, na↓ʃiɛ→ ts⁼aɪ↓iɛ↓↑ jʊŋ↓p⁼u↓ts`⁼ə ɥ↓↑ s`əŋ→xwo↑ t⁼ə kʰweɪ↓fa↑ ts⁼wo↓ t⁼oʊ↓ts`⁼əŋ→ t⁼ə ɹ`ən↑,
3.wav|999|tʰa→mən ts`⁼ɹ`→ts`⁼ʊŋ→ t⁼ə t⁼a↓t⁼wo→s`u↓ tsʰʊŋ↑k⁼ən→p⁼ən↓↑s`ɑŋ↓ xaɪ↑s`ɹ`↓ k⁼an↓↑tʃ⁼ɥɛ↑ mən↓mən↓p⁼u↓lə↓.
4.wav|999|tʃʰiŋ↑ʃiŋ↑ tʃ⁼joʊ↓ k⁼ən→ na↓ʃiɛ→ xaɪ↑ ts⁼aɪ↓ s`əŋ→xwo↑ t⁼ə kʰwən↓kʰu↓↑ ts`⁼ʊŋ→ p⁼wo↑t⁼oʊ↓ t⁼ə ɹ`ən↑ i↓p⁼an→ u↑i↓.
5.wav|999|tʰa→mən neɪ↓ts⁼aɪ↓ kʰʊŋ→ʃɥ→, k⁼an↓↑tʃ⁼ɥɛ↑ i↓s`ɹ`↑ t⁼aɪ→ts`⁼ɹ`↓, sɹ→ʃiɑŋ↓↑ kʰweɪ↓fa↑,
6.wav|999|ts`⁼ə↓ʃiɛ→ tʃ⁼joʊ↓ tʃʰɥ→s`ɹ`↓↑ tʰa→mən tʰoʊ↑ɹ`u↓ s`ə↓tʃ⁼iɑʊ→ ɹ`ən↑tʃʰɥn↑ ts`⁼ʊŋ→.
7.wav|999|ts⁼u↓↑ts`ʰəŋ↑ na↓ʃiɛ→ s`ə↓tʃ⁼iɑʊ→tʃʰɥæn→ts⁼ɹ t⁼ə ɹ`ən↑ iɛ↓↑ ts`⁼əŋ↓s`ɹ`↓ tʰa→mən ts`⁼ə↓ i→leɪ↓ t⁼ə ɹ`ən↑.
8.wav|999|“ in→weɪ↓ ʃiɑŋ→tʰʊŋ↑ ɥ↓↑mɑʊ↑ t⁼ə niɑʊ↓↑ tʃ⁼ɥ↓ ts⁼aɪ↓ i→kʰwaɪ↓”.
9.wav|999|tʰa→mən tʃ⁼ɥ↓ts⁼aɪ↓ i→kʰwaɪ↓ ts`⁼weɪ→ts`⁼u↑ ʃiɑʊ→tʃʰjɛn↓↑, ɥ↑lə↓.
10.wav|999|tʰa→mən i↓↑ fɑŋ↓ts⁼ʊŋ↓ k⁼an↓↑k⁼wan→ t⁼ə xwan→ɥ↑, tʃ⁼i↑tʃ⁼in↓↑ s`əŋ→sə↓ t⁼ə ʃiɑŋ↓↑s`oʊ↓ kʰaɪ→s`ɹ`↓↑,
11.wav|999|i↓↑ xuɑŋ→tʰɑŋ↑, u↑t⁼u↓ əɹ`↑ k⁼ɑʊ↓ts`⁼ʊŋ→.
12.wav|999|ts`⁼ʊŋ↓t⁼wo→ k⁼ɑŋ→k⁼ɑŋ→ tʰa↓ɹ`u↓ s`əŋ→xwo↑ t⁼ə wan↑kʰu↓ts⁼ɹ↓↑t⁼i↓ tʃʰjʊŋ↑s`ə→tʃ⁼i↑ɥ↓,
13.wav|999|ts⁼aɪ↓ liŋ↓ɹ`ən↑ nan↑i↓↑ts`⁼ɹ`↓ʃin↓ t⁼ə tʃ⁼i↑ t⁼wan↓↑s`ɹ`↑tʃ⁼jɛn→ neɪ↓ tʃ⁼joʊ↓ p⁼a↓↑ t⁼a↓p⁼u↓fən↓ tʃ⁼ja→tsʰaɪ↑ xweɪ→xwo↓ t⁼aɪ↓tʃ⁼in↓.
14.wav|999|ts`⁼ə↓ts`⁼ʊŋ↓↑ ts⁼wo↓pʰaɪ↓, tʃʰi↑ k⁼ən→ɥæn↑ tʃʰɥɛ↓s`ɹ`↑ p⁼u↑s`ɹ`↓ p⁼iɛ↑t⁼ə, ts`⁼əŋ↓s`ɹ`↓ u↑liɑʊ↑.
18.wav|999|tʰa→ ɥæn↑ts⁼ɹ↓ s`ɑŋ↓s`u↓ t⁼ə tʃ⁼iŋ→s`ən↑ pʰin↑fa↑ xə↑ kʰʊŋ→ʃɥ→.
16.wav|999|i↑k⁼ə↓ waɪ↓ ts⁼aɪ↓ fu↓joʊ↓↑, t⁼an↓ neɪ↓ts⁼aɪ↓ pʰin↑fa↑ t⁼ə fu↓tʃ⁼ja→ts⁼ɹ↓↑t⁼i↓ laɪ↑t⁼ɑʊ↓ ts`⁼ə↓k⁼ə↓ s`ɹ`↓tʃ⁼iɛ↓,
17.wav|999|xweɪ↓ tʰu↑lɑʊ↑t⁼i↓ jʊŋ↓waɪ↓ ts⁼aɪ↓ t⁼ə tsʰaɪ↑fu↓ tʃʰɥ↓ p⁼u↓↑ts`ʰɑŋ↑ neɪ↓ts⁼aɪ↓ t⁼ə p⁼u↓ts⁼u↑,
18.wav|999|tʰa→ kʰə↓↑uɑŋ↓ tsʰʊŋ↑ waɪ↓p⁼u↓ t⁼ə↑t⁼ɑʊ↓ i→tʃʰiɛ↓,
19.wav|999|ts`⁼ə↓ tʃʰiŋ↑ʃiŋ↑ tʃ⁼joʊ↓ xɑʊ↓↑p⁼i↓↑ s`ɹ`↓tʰu↑ i↓↑ s`ɑʊ↓nɥ↓↑ t⁼ə xan↓s`weɪ↓↑ tʃʰɥ↓ tʃʰiɑŋ↑tʃ⁼jɛn↓ ts⁼ɹ↓tʃ⁼i↓↑ tʰi↓↑pʰwo↓ t⁼ə lɑʊ↓↑ʃjoʊ↓↑ ts`⁼ɹ`→ ɹ`ən↑.
20.wav|999|ɹ`ən↑ ts⁼ɹ↓s`ən→ neɪ↓ts⁼aɪ↓ t⁼ə pʰin↑fa↑ joʊ↑tsʰɹ↓↑ t⁼ɑʊ↓↑ts`⁼ɹ`↓ lə waɪ↓ ts⁼aɪ↓ tsʰaɪ↑fu↓ t⁼ə pʰin↑fa↑.
21.wav|999|ts`⁼ɹ`↓ɥ↑ liŋ↓waɪ↓ liɑŋ↓↑ʃiɑŋ↓ ɹ`ən↑s`əŋ→ xɑʊ↓↑ts`ʰu↓ t⁼ə ts`⁼ʊŋ↓iɑʊ↓ʃiŋ↓,
22.wav|999|p⁼u↓ ʃɥ→iɑʊ↓ wo↓↑ tʰə↓p⁼iɛ↑tʃʰiɑŋ↑t⁼iɑʊ↓.
23.wav|999|tsʰaɪ↑ts`ʰan↓↑ t⁼ə tʃ⁼ja↓ts`⁼ɹ`↑ ts⁼aɪ↓ t⁼ɑŋ→tʃ⁼in→ s`ɹ`↓ ɹ`ən↑ swo↓↑ k⁼ʊŋ→ɹ`ən↓ t⁼ə,
24.wav|999|jʊŋ↓p⁼u↓ts`⁼ə weɪ↓ tʃʰi↑ ʃɥæn→ts`ʰwan↑ tʃ⁼iɛ↓s`ɑʊ↓.
25.wav|999|p⁼i↓↑tʃʰi↓↑ t⁼i↓əɹ`↓ʃiɑŋ↓ t⁼ə xɑʊ↓↑ts`ʰu↓,
26.wav|999|t⁼i↓san→ʃiɑŋ↓ t⁼ə xɑʊ↓↑ts`ʰu↓ tʃ⁼ɥ↓joʊ↓↑ i→ts`⁼ʊŋ↓↑ ʃiɑŋ→t⁼ɑŋ→ pʰiɑʊ→miɑʊ↓↑ t⁼ə ts`ʰəŋ↑fən↓,
27.wav|999|in→weɪ↓ miŋ↑ɥ↓, miŋ↑uɑŋ↓, t⁼i↓weɪ↓ t⁼əŋ↓↑.
28.wav|999|tʃʰɥæn↑ joʊ↑ tʰa→ɹ`ən↑ t⁼ə i↓tʃ⁼jɛn↓ k⁼oʊ↓ts`ʰəŋ↑.
29.wav|999|meɪ↓↑ɹ`ən↑ t⁼oʊ→ kʰə↓↑i↓↑ ts`⁼əŋ→tʃʰɥ↓↑ t⁼ə↑t⁼ɑʊ↓ miŋ↑ɥ↓,
30.wav|999|i↓ tʃ⁼i↑ tʃʰiŋ→p⁼aɪ↑ t⁼ə miŋ↑s`əŋ→,
31.wav|999|t⁼an↓ s`ə↓xweɪ↓ t⁼i↓weɪ↓, ts⁼ə↑ ts`⁼ɹ`↓↑joʊ↓↑ ɥɛ↓ pʰan↓ k⁼wo↑tʃ⁼ja→ ts`⁼əŋ↓fu↓↑ t⁼ə ɹ`ən↑tsʰaɪ↑ nəŋ↑ ɹ`an↓↑ts`⁼ɹ`↓↑,
32.wav|999|ts`⁼ɹ`↓ɥ↑ ʃjɛn↓↑xə↓ t⁼ə miŋ↑uɑŋ↓ tʃ⁼joʊ↓ ts`⁼ɹ`↓↑joʊ↓↑ tʃ⁼i↑s`ɑʊ↓↑s`u↓ ɹ`ən↑tsʰaɪ↑ xweɪ↓ t⁼ə↑t⁼ɑʊ↓.
33.wav|999|ts⁼aɪ↓ swo↓↑joʊ↓↑ ts`⁼ə↓ʃiɛ→ t⁼ɑŋ→ts`⁼ʊŋ→,
34.wav|999|miŋ↑ɥ↓ s`ɹ`↓ mi↑ts⁼u↑ts`⁼ən→k⁼weɪ↓ t⁼ə,
35.wav|999|ʃjɛn↓↑xə↓ t⁼ə miŋ↑uɑŋ↓ ts⁼ə↑ s`ɹ`↓ ɹ`ən↑ swo↓↑ ʃi→uɑŋ↓ t⁼ə↑t⁼ɑʊ↓ t⁼ə tʃ⁼ja↓ts`⁼ɹ`↑ ts`⁼ɹ`↓ɑŋ↑ t⁼ə t⁼ʊŋ→ʃi→,
36.wav|999|na↓ s`ɹ`↓ tʰjɛn→ts`⁼ɹ`→tʃ⁼iɑʊ→ts⁼ɹ tsʰaɪ↑nəŋ↑ t⁼ə↑t⁼ɑʊ↓ t⁼ə tʃ⁼in→ iɑŋ↑mɑʊ↑.
37.wav|999|liŋ↓i↓fɑŋ→mjɛn↓,
38.wav|999|ts`⁼ɹ`↓↑joʊ↓↑ s`a↓↑k⁼wa→ tsʰaɪ↑ xweɪ↓ p⁼a↓↑ s`ə↓xweɪ↓ t⁼i↓weɪ↓ fɑŋ↓ts`⁼ɹ`↓ ts⁼aɪ↓ tsʰaɪ↑ts`ʰan↓↑ ts`⁼ɹ`→tʃʰjɛn↑.
39.wav|999|liŋ↓waɪ↓, ɹ`ən↑ jʊŋ→joʊ↓↑ t⁼ə tsʰaɪ↑ts`ʰan↓↑, u↓pʰin↓↑ xə↑ miŋ↑ɥ↓, s`əŋ→uɑŋ↓,
40.wav|999|s`ɹ`↓ ts`ʰu↓↑ɥ↑ i→ts`⁼ʊŋ↓↑ swo↓↑weɪ↓ t⁼ə xu↓weɪ↓ iŋ↓↑ʃiɑŋ↓↑, tsʰu↓tʃ⁼in↓ t⁼ə k⁼wan→ʃi↓.
41.wav|999|p⁼i↓↑t⁼ə↑ ni↑sɹ→ s`wo→ k⁼wo↓,“ i↑k⁼ə↓ ɹ`ən↑ swo↓↑ jʊŋ→joʊ↓↑ t⁼ə tsʰaɪ↑ts`ʰan↓↑ tʃ⁼ɥɛ↑t⁼iŋ↓ lə ts`⁼ə↓k⁼ə↓ ɹ`ən↑ ts⁼aɪ↓ tʰa→ɹ`ən↑ jɛn↓↑ts`⁼ʊŋ→ t⁼ə tʃ⁼ja↓ts`⁼ɹ`↑”.
42.wav|999|ɹ`u↑k⁼wo↓↑ ts`⁼ə↓tʃ⁼ɥ↓ xwa↓ s`ɹ`↓ ts`⁼əŋ↓tʃʰɥɛ↓ t⁼əxwa↓,
43.wav|999|na↓mə, fan↓↑k⁼wo↓laɪ↑, tʰa→ɹ`ən↑ t⁼weɪ↓ ts⁼ɹ↓tʃ⁼i↓↑ t⁼ə liɑŋ↑xɑʊ↓↑ pʰiŋ↑tʃ⁼ja↓,
44.wav|999|nəŋ↑i↓↑ k⁼ə↓ts`⁼ʊŋ↓↑ ʃiŋ↑s`ɹ`↓ p⁼ɑŋ→ts`⁼u↓ ts⁼ɹ↓tʃ⁼i↓↑ xwo↓tʃʰɥ↓↑ tsʰaɪ↑ts`ʰan↓↑.
user_voice_collect.py
+71
View File
@@ -0,0 +1,71 @@
import numpy as np
import torch
import torchaudio
import gradio as gr
anno_lines = []
with open("./user_voice/user_voice.txt", 'r', encoding='utf-8') as f:
for line in f.readlines():
anno_lines.append(line.strip("\n"))
text_index = 0
def display_text(index):
index = int(index)
global text_index
text_index = index
return f"{text_index}: " + anno_lines[index].split("|")[2].strip("[ZH]")
def display_prev_text():
global text_index
if text_index != 0:
text_index -= 1
return f"{text_index}: " + anno_lines[text_index].split("|")[2].strip("[ZH]")
def display_next_text():
global text_index
if text_index != len(anno_lines)-1:
text_index += 1
return f"{text_index}: " + anno_lines[text_index].split("|")[2].strip("[ZH]")
def save_audio(audio):
global text_index
if audio:
sr, wav = audio
wav = torch.tensor(wav).type(torch.float32) / max(wav.max(), -wav.min())
wav = wav.unsqueeze(0) if len(wav.shape) == 1 else wav
if sr != 22050:
res_wav = torchaudio.transforms.Resample(orig_freq=sr, new_freq=22050)(wav)
else:
res_wav = wav
torchaudio.save(f"./user_voice/{str(text_index)}.wav", res_wav, 22050, channels_first=True)
return f"Audio saved to ./user_voice/{str(text_index)}.wav successfully!"
else:
return "Error: Please record your audio!"
if __name__ == "__main__":
app = gr.Blocks()
with app:
with gr.Row():
text = gr.Textbox(value="0: " + anno_lines[0].split("|")[2].strip("[ZH]"), label="Please read the text here")
with gr.Row():
audio_to_collect = gr.Audio(source="microphone")
with gr.Row():
with gr.Column():
prev_btn = gr.Button(value="Previous")
with gr.Column():
next_btn = gr.Button(value="Next")
with gr.Row():
index_dropdown = gr.Dropdown(choices=[str(i) for i in range(len(anno_lines))], value="0",
label="No. of text", interactive=True)
with gr.Row():
with gr.Column():
save_btn = gr.Button(value="Save Audio")
with gr.Column():
audio_save_message = gr.Textbox(label="Message")
index_dropdown.change(display_text, inputs=index_dropdown, outputs=text)
prev_btn.click(display_prev_text, inputs=None, outputs=text)
next_btn.click(display_next_text, inputs=None, outputs=text)
save_btn.click(save_audio, inputs=audio_to_collect, outputs=audio_save_message)
app.launch()