Add voice parts image to README

This commit is contained in:
Michael Hansen 2022-04-11 14:03:39 -04:00
commit 3eb5d99a56
3 changed files with 295 additions and 2 deletions

View file

@ -119,11 +119,13 @@ Once installed, the following commands will be available in `.venv/bin`:
Mimic 3 references voices with the format:
* `<language>/<name>_<quality>` for single speaker voices, and
* `<language>/<name>_<quality>#<speaker>` for multi-speaker voices
* `<language>/<dataset>_<quality>` for single speaker voices, and
* `<language>/<dataset>_<quality>#<speaker>` for multi-speaker voices
* `<speaker>` can be a name or number starting at 0
* Speaker names come from a voice's `speakers.txt` file
![parts of a mimic 3 voice](img/voice_parts.png)
For example, the default [Alan Pope](https://popey.me/) voice key is `en_UK/apope_low`.
The [CMU Arctic voice](https://github.com/MycroftAI/mimic3-voices/tree/master/voices/en_US/cmu-arctic_low) contains multiple speakers, with a commonly used voice being `en_US/cmu-arctic_low#slt`.

BIN
img/voice_parts.png Normal file

Binary file not shown.

After

Width:  |  Height:  |  Size: 36 KiB

291
img/voice_parts.svg Normal file
View file

@ -0,0 +1,291 @@
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<svg
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:cc="http://creativecommons.org/ns#"
xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
xmlns:svg="http://www.w3.org/2000/svg"
xmlns="http://www.w3.org/2000/svg"
xmlns:sodipodi="http://sodipodi.sourceforge.net/DTD/sodipodi-0.dtd"
xmlns:inkscape="http://www.inkscape.org/namespaces/inkscape"
width="196.52223mm"
height="86.877838mm"
viewBox="0 0 196.52223 86.877838"
version="1.1"
id="svg8"
inkscape:version="1.0.2 (e86c870879, 2021-01-15)"
sodipodi:docname="voice_parts.svg"
inkscape:export-filename="./voice_parts.png"
inkscape:export-xdpi="90"
inkscape:export-ydpi="90">
<defs
id="defs2">
<marker
style="overflow:visible"
id="marker1492"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="TriangleOutM"
inkscape:isstock="true">
<path
transform="scale(0.4)"
style="fill:#5b6984;fill-opacity:1;fill-rule:evenodd;stroke:#5b6984;stroke-width:1pt;stroke-opacity:1"
d="M 5.77,0 -2.88,5 V -5 Z"
id="path1490" />
</marker>
<marker
style="overflow:visible"
id="marker1422"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="TriangleOutM"
inkscape:isstock="true">
<path
transform="scale(0.4)"
style="fill:#fd9e66;fill-opacity:1;fill-rule:evenodd;stroke:#fd9e66;stroke-width:1pt;stroke-opacity:1"
d="M 5.77,0 -2.88,5 V -5 Z"
id="path1420" />
</marker>
<marker
style="overflow:visible"
id="marker1348"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="TriangleOutM"
inkscape:isstock="true"
inkscape:collect="always">
<path
transform="scale(0.4)"
style="fill:#fd9e66;fill-opacity:1;fill-rule:evenodd;stroke:#fd9e66;stroke-width:1pt;stroke-opacity:1"
d="M 5.77,0 -2.88,5 V -5 Z"
id="path1346" />
</marker>
<marker
style="overflow:visible"
id="marker1258"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="TriangleOutM"
inkscape:isstock="true"
inkscape:collect="always">
<path
transform="scale(0.4)"
style="fill:#40dbb0;fill-opacity:1;fill-rule:evenodd;stroke:#40dbb0;stroke-width:1pt;stroke-opacity:1"
d="M 5.77,0 -2.88,5 V -5 Z"
id="path1256" />
</marker>
<marker
style="overflow:visible"
id="TriangleOutM"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="TriangleOutM"
inkscape:isstock="true"
inkscape:collect="always">
<path
transform="scale(0.4)"
style="fill:#22a7f0;fill-opacity:1;fill-rule:evenodd;stroke:#22a7f0;stroke-width:1pt;stroke-opacity:1"
d="M 5.77,0 -2.88,5 V -5 Z"
id="path1049" />
</marker>
<marker
style="overflow:visible"
id="DotS"
refX="0"
refY="0"
orient="auto"
inkscape:stockid="DotS"
inkscape:isstock="true">
<path
transform="matrix(0.2,0,0,0.2,1.48,0.2)"
style="fill:#22a7f0;fill-opacity:1;fill-rule:evenodd;stroke:#22a7f0;stroke-width:1pt;stroke-opacity:1"
d="m -2.5,-1 c 0,2.76 -2.24,5 -5,5 -2.76,0 -5,-2.24 -5,-5 0,-2.76 2.24,-5 5,-5 2.76,0 5,2.24 5,5 z"
id="path971" />
</marker>
</defs>
<sodipodi:namedview
id="base"
pagecolor="#ffffff"
bordercolor="#666666"
borderopacity="1.0"
inkscape:pageopacity="1"
inkscape:pageshadow="2"
inkscape:zoom="0.73228114"
inkscape:cx="356.43322"
inkscape:cy="456.02474"
inkscape:document-units="mm"
inkscape:current-layer="layer1"
inkscape:document-rotation="0"
showgrid="false"
inkscape:window-width="1920"
inkscape:window-height="1012"
inkscape:window-x="0"
inkscape:window-y="147"
inkscape:window-maximized="1"
inkscape:snap-global="false"
fit-margin-top="5"
fit-margin-left="5"
fit-margin-right="5"
fit-margin-bottom="5" />
<metadata
id="metadata5">
<rdf:RDF>
<cc:Work
rdf:about="">
<dc:format>image/svg+xml</dc:format>
<dc:type
rdf:resource="http://purl.org/dc/dcmitype/StillImage" />
<dc:title></dc:title>
</cc:Work>
</rdf:RDF>
</metadata>
<g
inkscape:label="Layer 1"
inkscape:groupmode="layer"
id="layer1"
transform="translate(-10.693711,-27.843453)">
<text
xml:space="preserve"
style="font-style:normal;font-weight:normal;font-size:12.6489px;line-height:1.25;font-family:sans-serif;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="14.996842"
y="78.850319"
id="text844"><tspan
sodipodi:role="line"
id="tspan842"
x="14.996842"
y="78.850319"
style="font-style:normal;font-variant:normal;font-weight:bold;font-stretch:normal;font-size:12.6489px;font-family:'Noto Mono';-inkscape-font-specification:'Noto Mono, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;stroke-width:0.264583"><tspan
style="fill:#22a7f0;fill-opacity:1"
id="tspan898">en</tspan>_<tspan
style="fill:#40dbb0;fill-opacity:1"
id="tspan900">US</tspan>/<tspan
style="fill:#d81159;fill-opacity:1"
id="tspan1332">cmu-arctic</tspan>_<tspan
style="fill:#fd9e66;fill-opacity:1"
id="tspan1334">low</tspan><tspan
style="fill:#5b6984;fill-opacity:1"
id="tspan1336">#slt</tspan></tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="14.79413"
y="40.886761"
id="text866"><tspan
sodipodi:role="line"
id="tspan864"
x="14.79413"
y="40.886761"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#22a7f0;fill-opacity:1;stroke-width:0.264583">language</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="29.455219"
y="107.05959"
id="text870"><tspan
sodipodi:role="line"
id="tspan868"
x="29.455219"
y="107.05959"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#40dbb0;fill-opacity:1;stroke-width:0.264583">region</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#d81159;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="80.094269"
y="53.571114"
id="text874"><tspan
sodipodi:role="line"
id="tspan872"
x="80.094269"
y="53.571114"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#d81159;fill-opacity:1;stroke-width:0.264583">dataset</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="138.57475"
y="107.1813"
id="text878"><tspan
sodipodi:role="line"
id="tspan876"
x="138.57475"
y="107.1813"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#fd9e66;fill-opacity:1;stroke-width:0.264583">quality</tspan></text>
<g
id="g896"
transform="translate(8.2019951,-7.2134018)">
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="154.69705"
y="48.100163"
id="text882"><tspan
sodipodi:role="line"
x="154.69705"
y="48.100163"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:10.5833px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#5b6984;fill-opacity:1;stroke-width:0.264583"
id="tspan884">speaker</tspan></text>
<text
xml:space="preserve"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:7.78077px;line-height:1.25;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;fill:#000000;fill-opacity:1;stroke:none;stroke-width:0.264583"
x="157.19258"
y="58.11293"
id="text890"><tspan
sodipodi:role="line"
x="157.19258"
y="58.11293"
style="font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;font-size:7.78077px;font-family:'Noto Sans';-inkscape-font-specification:'Noto Sans, Normal';font-variant-ligatures:normal;font-variant-caps:normal;font-variant-numeric:normal;font-variant-east-asian:normal;stroke-width:0.264583"
id="tspan888">(optional)</tspan></text>
</g>
<path
style="fill:none;stroke:#22a7f0;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#TriangleOutM)"
d="m 23.630172,44.360274 c -4.750276,2.202342 -8.862913,16.129795 -4.822889,22.231261"
id="path902"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#40dbb0;stroke-width:0.999995;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#marker1258)"
d="M 45.63177,98.711512 V 84.770101"
id="path1254"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#fd9e66;stroke-width:0.999995;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#marker1348)"
d="M 155.6985,98.711512 V 84.770101"
id="path1344"
sodipodi:nodetypes="cc" />
<path
style="fill:none;stroke:#fd9e66;stroke-width:0.999995;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1;marker-end:url(#marker1422)"
d="M 155.6985,98.711512 V 84.770101"
id="path1418"
sodipodi:nodetypes="cc" />
<g
id="g1621">
<path
id="rect1614"
style="fill:none;fill-opacity:1;stroke:#d81159;stroke-width:1;stroke-linecap:round;stroke-miterlimit:4;stroke-dasharray:none;stroke-opacity:1"
d="m 63.831116,67.523986 v -5.309692 h 71.305004 v 5.309692"
sodipodi:nodetypes="cccc" />
<path
style="fill:none;stroke:#d81159;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1"
d="M 99.483618,62.485489 V 57.10005"
id="path1617"
sodipodi:nodetypes="cc" />
</g>
<g
id="g1627"
transform="translate(104.24583)"
style="stroke:#5b6984;stroke-opacity:1">
<path
id="path1623"
style="fill:none;fill-opacity:1;stroke:#5b6984;stroke-width:1;stroke-linecap:round;stroke-miterlimit:4;stroke-dasharray:3, 3;stroke-dashoffset:0;stroke-opacity:1"
d="M 64.360283,67.523986 V 62.214294 H 92.27362 v 5.309692"
sodipodi:nodetypes="cccc" />
<path
style="fill:none;stroke:#5b6984;stroke-width:1;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-dasharray:3, 3;stroke-dashoffset:0;stroke-opacity:1"
d="M 78.581536,62.485489 V 52.866717"
id="path1625"
sodipodi:nodetypes="cc" />
</g>
</g>
</svg>

After

Width:  |  Height:  |  Size: 14 KiB