mirror of
https://github.com/wassname/TTS.git
synced 2026-10-27 12:30:27 +08:00
Add Bokeh interactive plotting
This commit is contained in:
nmstoker committed
1 parent
b89d04c151
commit
58bf3244ac
2 files changed
+627
-70
No files matched your search
@@ -28,7 +28,7 @@ parser.add_argument(
|
||||
parser.add_argument(
|
||||
'data_path',
|
||||
type=str,
|
||||
help='Defines the data path. It overwrites config.json.')
|
||||
help='Data path for wav files - directory or CSV file')
|
||||
parser.add_argument(
|
||||
'output_path',
|
||||
type=str,
|
||||
@@ -36,14 +36,42 @@ parser.add_argument(
|
||||
parser.add_argument(
|
||||
'--use_cuda', type=bool, help='flag to set cuda.', default=False
|
||||
)
|
||||
parser.add_argument(
|
||||
'--separator', type=str, help='Separator used in file if CSV is passed for data_path', default='|'
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
|
||||
c = load_config(args.config_path)
|
||||
ap = AudioProcessor(**c['audio'])
|
||||
|
||||
wav_files = glob.glob(args.data_path + '/**/*.wav', recursive=True)
|
||||
output_files = [wav_file.replace(args.data_path, args.output_path).replace(
|
||||
data_path = args.data_path
|
||||
split_ext = os.path.splitext(data_path)
|
||||
sep = args.separator
|
||||
|
||||
if len(split_ext) > 0 and split_ext[1].lower() == '.csv':
|
||||
# Parse CSV
|
||||
print(f'CSV file: {data_path}')
|
||||
with open(data_path) as f:
|
||||
wav_path = os.path.join(os.path.dirname(data_path), 'wavs')
|
||||
wav_files = []
|
||||
print(f'Separator is: {sep}')
|
||||
for line in f:
|
||||
components = line.split(sep)
|
||||
if len(components) != 2:
|
||||
print("Invalid line")
|
||||
continue
|
||||
wav_file = os.path.join(wav_path, components[0] + '.wav')
|
||||
#print(f'wav_file: {wav_file}')
|
||||
if os.path.exists(wav_file):
|
||||
wav_files.append(wav_file)
|
||||
print(f'Count of wavs imported: {len(wav_files)}')
|
||||
else:
|
||||
# Parse all wav files in data_path
|
||||
wav_path = data_path
|
||||
wav_files = glob.glob(data_path + '/**/*.wav', recursive=True)
|
||||
|
||||
output_files = [wav_file.replace(wav_path, args.output_path).replace(
|
||||
'.wav', '.npy') for wav_file in wav_files]
|
||||
|
||||
for output_file in output_files:
|
||||
|
||||
@@ -1,27 +1,421 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Overview\n",
|
||||
"\n",
|
||||
"This notebook can be used with both a single or multi- speaker corpus and allows the interactive plotting of speaker embeddings linked to underlying audio (see instructions in the repo's speaker_embedding directory)\n",
|
||||
"\n",
|
||||
"Depending on the directory structure used for your corpus, you may need to adjust handling of **speaker_to_utter** and **locations**."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import glob\n",
|
||||
"import random\n",
|
||||
"import numpy as np\n",
|
||||
"import torch\n",
|
||||
"import umap\n",
|
||||
"\n",
|
||||
"from TTS.speaker_encoder.model import SpeakerEncoder\n",
|
||||
"from TTS.utils.audio import AudioProcessor\n",
|
||||
"from TTS.utils.generic_utils import load_config\n",
|
||||
"\n",
|
||||
"from bokeh.io import output_notebook, show\n",
|
||||
"from bokeh.plotting import figure\n",
|
||||
"from bokeh.models import HoverTool, ColumnDataSource, BoxZoomTool, ResetTool, OpenURL, TapTool\n",
|
||||
"from bokeh.transform import factor_cmap, factor_mark\n",
|
||||
"from bokeh.palettes import Category10"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"For larger sets of speakers, you can use **Category20**, but you need to change it in the **pal** variable too\n",
|
||||
"\n",
|
||||
"List of Bokeh palettes here: http://docs.bokeh.org/en/1.4.0/docs/reference/palettes.html\n",
|
||||
"\n",
|
||||
"**NB:** if you have problems with other palettes, first see https://stackoverflow.com/questions/48333820/why-do-some-bokeh-palettes-raise-a-valueerror-when-used-in-factor-cmap"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"\n",
|
||||
" <div class=\"bk-root\">\n",
|
||||
" <a href=\"https://bokeh.pydata.org\" target=\"_blank\" class=\"bk-logo bk-logo-small bk-logo-notebook\"></a>\n",
|
||||
" <span id=\"1001\">Loading BokehJS ...</span>\n",
|
||||
" </div>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"application/javascript": [
|
||||
"\n",
|
||||
"(function(root) {\n",
|
||||
" function now() {\n",
|
||||
" return new Date();\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" var force = true;\n",
|
||||
"\n",
|
||||
" if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n",
|
||||
" root._bokeh_onload_callbacks = [];\n",
|
||||
" root._bokeh_is_loading = undefined;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" var JS_MIME_TYPE = 'application/javascript';\n",
|
||||
" var HTML_MIME_TYPE = 'text/html';\n",
|
||||
" var EXEC_MIME_TYPE = 'application/vnd.bokehjs_exec.v0+json';\n",
|
||||
" var CLASS_NAME = 'output_bokeh rendered_html';\n",
|
||||
"\n",
|
||||
" /**\n",
|
||||
" * Render data to the DOM node\n",
|
||||
" */\n",
|
||||
" function render(props, node) {\n",
|
||||
" var script = document.createElement(\"script\");\n",
|
||||
" node.appendChild(script);\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" /**\n",
|
||||
" * Handle when an output is cleared or removed\n",
|
||||
" */\n",
|
||||
" function handleClearOutput(event, handle) {\n",
|
||||
" var cell = handle.cell;\n",
|
||||
"\n",
|
||||
" var id = cell.output_area._bokeh_element_id;\n",
|
||||
" var server_id = cell.output_area._bokeh_server_id;\n",
|
||||
" // Clean up Bokeh references\n",
|
||||
" if (id != null && id in Bokeh.index) {\n",
|
||||
" Bokeh.index[id].model.document.clear();\n",
|
||||
" delete Bokeh.index[id];\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" if (server_id !== undefined) {\n",
|
||||
" // Clean up Bokeh references\n",
|
||||
" var cmd = \"from bokeh.io.state import curstate; print(curstate().uuid_to_server['\" + server_id + \"'].get_sessions()[0].document.roots[0]._id)\";\n",
|
||||
" cell.notebook.kernel.execute(cmd, {\n",
|
||||
" iopub: {\n",
|
||||
" output: function(msg) {\n",
|
||||
" var id = msg.content.text.trim();\n",
|
||||
" if (id in Bokeh.index) {\n",
|
||||
" Bokeh.index[id].model.document.clear();\n",
|
||||
" delete Bokeh.index[id];\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" });\n",
|
||||
" // Destroy server and session\n",
|
||||
" var cmd = \"import bokeh.io.notebook as ion; ion.destroy_server('\" + server_id + \"')\";\n",
|
||||
" cell.notebook.kernel.execute(cmd);\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" /**\n",
|
||||
" * Handle when a new output is added\n",
|
||||
" */\n",
|
||||
" function handleAddOutput(event, handle) {\n",
|
||||
" var output_area = handle.output_area;\n",
|
||||
" var output = handle.output;\n",
|
||||
"\n",
|
||||
" // limit handleAddOutput to display_data with EXEC_MIME_TYPE content only\n",
|
||||
" if ((output.output_type != \"display_data\") || (!output.data.hasOwnProperty(EXEC_MIME_TYPE))) {\n",
|
||||
" return\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" var toinsert = output_area.element.find(\".\" + CLASS_NAME.split(' ')[0]);\n",
|
||||
"\n",
|
||||
" if (output.metadata[EXEC_MIME_TYPE][\"id\"] !== undefined) {\n",
|
||||
" toinsert[toinsert.length - 1].firstChild.textContent = output.data[JS_MIME_TYPE];\n",
|
||||
" // store reference to embed id on output_area\n",
|
||||
" output_area._bokeh_element_id = output.metadata[EXEC_MIME_TYPE][\"id\"];\n",
|
||||
" }\n",
|
||||
" if (output.metadata[EXEC_MIME_TYPE][\"server_id\"] !== undefined) {\n",
|
||||
" var bk_div = document.createElement(\"div\");\n",
|
||||
" bk_div.innerHTML = output.data[HTML_MIME_TYPE];\n",
|
||||
" var script_attrs = bk_div.children[0].attributes;\n",
|
||||
" for (var i = 0; i < script_attrs.length; i++) {\n",
|
||||
" toinsert[toinsert.length - 1].firstChild.setAttribute(script_attrs[i].name, script_attrs[i].value);\n",
|
||||
" }\n",
|
||||
" // store reference to server id on output_area\n",
|
||||
" output_area._bokeh_server_id = output.metadata[EXEC_MIME_TYPE][\"server_id\"];\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" function register_renderer(events, OutputArea) {\n",
|
||||
"\n",
|
||||
" function append_mime(data, metadata, element) {\n",
|
||||
" // create a DOM node to render to\n",
|
||||
" var toinsert = this.create_output_subarea(\n",
|
||||
" metadata,\n",
|
||||
" CLASS_NAME,\n",
|
||||
" EXEC_MIME_TYPE\n",
|
||||
" );\n",
|
||||
" this.keyboard_manager.register_events(toinsert);\n",
|
||||
" // Render to node\n",
|
||||
" var props = {data: data, metadata: metadata[EXEC_MIME_TYPE]};\n",
|
||||
" render(props, toinsert[toinsert.length - 1]);\n",
|
||||
" element.append(toinsert);\n",
|
||||
" return toinsert\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" /* Handle when an output is cleared or removed */\n",
|
||||
" events.on('clear_output.CodeCell', handleClearOutput);\n",
|
||||
" events.on('delete.Cell', handleClearOutput);\n",
|
||||
"\n",
|
||||
" /* Handle when a new output is added */\n",
|
||||
" events.on('output_added.OutputArea', handleAddOutput);\n",
|
||||
"\n",
|
||||
" /**\n",
|
||||
" * Register the mime type and append_mime function with output_area\n",
|
||||
" */\n",
|
||||
" OutputArea.prototype.register_mime_type(EXEC_MIME_TYPE, append_mime, {\n",
|
||||
" /* Is output safe? */\n",
|
||||
" safe: true,\n",
|
||||
" /* Index of renderer in `output_area.display_order` */\n",
|
||||
" index: 0\n",
|
||||
" });\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" // register the mime type if in Jupyter Notebook environment and previously unregistered\n",
|
||||
" if (root.Jupyter !== undefined) {\n",
|
||||
" var events = require('base/js/events');\n",
|
||||
" var OutputArea = require('notebook/js/outputarea').OutputArea;\n",
|
||||
"\n",
|
||||
" if (OutputArea.prototype.mime_types().indexOf(EXEC_MIME_TYPE) == -1) {\n",
|
||||
" register_renderer(events, OutputArea);\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" \n",
|
||||
" if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n",
|
||||
" root._bokeh_timeout = Date.now() + 5000;\n",
|
||||
" root._bokeh_failed_load = false;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" var NB_LOAD_WARNING = {'data': {'text/html':\n",
|
||||
" \"<div style='background-color: #fdd'>\\n\"+\n",
|
||||
" \"<p>\\n\"+\n",
|
||||
" \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n",
|
||||
" \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n",
|
||||
" \"</p>\\n\"+\n",
|
||||
" \"<ul>\\n\"+\n",
|
||||
" \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n",
|
||||
" \"<li>use INLINE resources instead, as so:</li>\\n\"+\n",
|
||||
" \"</ul>\\n\"+\n",
|
||||
" \"<code>\\n\"+\n",
|
||||
" \"from bokeh.resources import INLINE\\n\"+\n",
|
||||
" \"output_notebook(resources=INLINE)\\n\"+\n",
|
||||
" \"</code>\\n\"+\n",
|
||||
" \"</div>\"}};\n",
|
||||
"\n",
|
||||
" function display_loaded() {\n",
|
||||
" var el = document.getElementById(\"1001\");\n",
|
||||
" if (el != null) {\n",
|
||||
" el.textContent = \"BokehJS is loading...\";\n",
|
||||
" }\n",
|
||||
" if (root.Bokeh !== undefined) {\n",
|
||||
" if (el != null) {\n",
|
||||
" el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n",
|
||||
" }\n",
|
||||
" } else if (Date.now() < root._bokeh_timeout) {\n",
|
||||
" setTimeout(display_loaded, 100)\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" function run_callbacks() {\n",
|
||||
" try {\n",
|
||||
" root._bokeh_onload_callbacks.forEach(function(callback) {\n",
|
||||
" if (callback != null)\n",
|
||||
" callback();\n",
|
||||
" });\n",
|
||||
" } finally {\n",
|
||||
" delete root._bokeh_onload_callbacks\n",
|
||||
" }\n",
|
||||
" console.debug(\"Bokeh: all callbacks have finished\");\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" function load_libs(css_urls, js_urls, callback) {\n",
|
||||
" if (css_urls == null) css_urls = [];\n",
|
||||
" if (js_urls == null) js_urls = [];\n",
|
||||
"\n",
|
||||
" root._bokeh_onload_callbacks.push(callback);\n",
|
||||
" if (root._bokeh_is_loading > 0) {\n",
|
||||
" console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n",
|
||||
" return null;\n",
|
||||
" }\n",
|
||||
" if (js_urls == null || js_urls.length === 0) {\n",
|
||||
" run_callbacks();\n",
|
||||
" return null;\n",
|
||||
" }\n",
|
||||
" console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n",
|
||||
" root._bokeh_is_loading = css_urls.length + js_urls.length;\n",
|
||||
"\n",
|
||||
" function on_load() {\n",
|
||||
" root._bokeh_is_loading--;\n",
|
||||
" if (root._bokeh_is_loading === 0) {\n",
|
||||
" console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n",
|
||||
" run_callbacks()\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" function on_error() {\n",
|
||||
" console.error(\"failed to load \" + url);\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" for (var i = 0; i < css_urls.length; i++) {\n",
|
||||
" var url = css_urls[i];\n",
|
||||
" const element = document.createElement(\"link\");\n",
|
||||
" element.onload = on_load;\n",
|
||||
" element.onerror = on_error;\n",
|
||||
" element.rel = \"stylesheet\";\n",
|
||||
" element.type = \"text/css\";\n",
|
||||
" element.href = url;\n",
|
||||
" console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n",
|
||||
" document.body.appendChild(element);\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" for (var i = 0; i < js_urls.length; i++) {\n",
|
||||
" var url = js_urls[i];\n",
|
||||
" var element = document.createElement('script');\n",
|
||||
" element.onload = on_load;\n",
|
||||
" element.onerror = on_error;\n",
|
||||
" element.async = false;\n",
|
||||
" element.src = url;\n",
|
||||
" console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n",
|
||||
" document.head.appendChild(element);\n",
|
||||
" }\n",
|
||||
" };var element = document.getElementById(\"1001\");\n",
|
||||
" if (element == null) {\n",
|
||||
" console.error(\"Bokeh: ERROR: autoload.js configured with elementid '1001' but no matching script tag was found. \")\n",
|
||||
" return false;\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" function inject_raw_css(css) {\n",
|
||||
" const element = document.createElement(\"style\");\n",
|
||||
" element.appendChild(document.createTextNode(css));\n",
|
||||
" document.body.appendChild(element);\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-1.3.4.min.js\"];\n",
|
||||
" var css_urls = [];\n",
|
||||
"\n",
|
||||
" var inline_js = [\n",
|
||||
" function(Bokeh) {\n",
|
||||
" Bokeh.set_log_level(\"info\");\n",
|
||||
" },\n",
|
||||
" \n",
|
||||
" function(Bokeh) {\n",
|
||||
" \n",
|
||||
" },\n",
|
||||
" function(Bokeh) {} // ensure no trailing comma for IE\n",
|
||||
" ];\n",
|
||||
"\n",
|
||||
" function run_inline_js() {\n",
|
||||
" \n",
|
||||
" if ((root.Bokeh !== undefined) || (force === true)) {\n",
|
||||
" for (var i = 0; i < inline_js.length; i++) {\n",
|
||||
" inline_js[i].call(root, root.Bokeh);\n",
|
||||
" }if (force === true) {\n",
|
||||
" display_loaded();\n",
|
||||
" }} else if (Date.now() < root._bokeh_timeout) {\n",
|
||||
" setTimeout(run_inline_js, 100);\n",
|
||||
" } else if (!root._bokeh_failed_load) {\n",
|
||||
" console.log(\"Bokeh: BokehJS failed to load within specified timeout.\");\n",
|
||||
" root._bokeh_failed_load = true;\n",
|
||||
" } else if (force !== true) {\n",
|
||||
" var cell = $(document.getElementById(\"1001\")).parents('.cell').data().cell;\n",
|
||||
" cell.output_area.append_execute_result(NB_LOAD_WARNING)\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" if (root._bokeh_is_loading === 0) {\n",
|
||||
" console.debug(\"Bokeh: BokehJS loaded, going straight to plotting\");\n",
|
||||
" run_inline_js();\n",
|
||||
" } else {\n",
|
||||
" load_libs(css_urls, js_urls, function() {\n",
|
||||
" console.debug(\"Bokeh: BokehJS plotting callback run at\", now());\n",
|
||||
" run_inline_js();\n",
|
||||
" });\n",
|
||||
" }\n",
|
||||
"}(window));"
|
||||
],
|
||||
"application/vnd.bokehjs_load.v0+json": "\n(function(root) {\n function now() {\n return new Date();\n }\n\n var force = true;\n\n if (typeof root._bokeh_onload_callbacks === \"undefined\" || force === true) {\n root._bokeh_onload_callbacks = [];\n root._bokeh_is_loading = undefined;\n }\n\n \n\n \n if (typeof (root._bokeh_timeout) === \"undefined\" || force === true) {\n root._bokeh_timeout = Date.now() + 5000;\n root._bokeh_failed_load = false;\n }\n\n var NB_LOAD_WARNING = {'data': {'text/html':\n \"<div style='background-color: #fdd'>\\n\"+\n \"<p>\\n\"+\n \"BokehJS does not appear to have successfully loaded. If loading BokehJS from CDN, this \\n\"+\n \"may be due to a slow or bad network connection. Possible fixes:\\n\"+\n \"</p>\\n\"+\n \"<ul>\\n\"+\n \"<li>re-rerun `output_notebook()` to attempt to load from CDN again, or</li>\\n\"+\n \"<li>use INLINE resources instead, as so:</li>\\n\"+\n \"</ul>\\n\"+\n \"<code>\\n\"+\n \"from bokeh.resources import INLINE\\n\"+\n \"output_notebook(resources=INLINE)\\n\"+\n \"</code>\\n\"+\n \"</div>\"}};\n\n function display_loaded() {\n var el = document.getElementById(\"1001\");\n if (el != null) {\n el.textContent = \"BokehJS is loading...\";\n }\n if (root.Bokeh !== undefined) {\n if (el != null) {\n el.textContent = \"BokehJS \" + root.Bokeh.version + \" successfully loaded.\";\n }\n } else if (Date.now() < root._bokeh_timeout) {\n setTimeout(display_loaded, 100)\n }\n }\n\n\n function run_callbacks() {\n try {\n root._bokeh_onload_callbacks.forEach(function(callback) {\n if (callback != null)\n callback();\n });\n } finally {\n delete root._bokeh_onload_callbacks\n }\n console.debug(\"Bokeh: all callbacks have finished\");\n }\n\n function load_libs(css_urls, js_urls, callback) {\n if (css_urls == null) css_urls = [];\n if (js_urls == null) js_urls = [];\n\n root._bokeh_onload_callbacks.push(callback);\n if (root._bokeh_is_loading > 0) {\n console.debug(\"Bokeh: BokehJS is being loaded, scheduling callback at\", now());\n return null;\n }\n if (js_urls == null || js_urls.length === 0) {\n run_callbacks();\n return null;\n }\n console.debug(\"Bokeh: BokehJS not loaded, scheduling load and callback at\", now());\n root._bokeh_is_loading = css_urls.length + js_urls.length;\n\n function on_load() {\n root._bokeh_is_loading--;\n if (root._bokeh_is_loading === 0) {\n console.debug(\"Bokeh: all BokehJS libraries/stylesheets loaded\");\n run_callbacks()\n }\n }\n\n function on_error() {\n console.error(\"failed to load \" + url);\n }\n\n for (var i = 0; i < css_urls.length; i++) {\n var url = css_urls[i];\n const element = document.createElement(\"link\");\n element.onload = on_load;\n element.onerror = on_error;\n element.rel = \"stylesheet\";\n element.type = \"text/css\";\n element.href = url;\n console.debug(\"Bokeh: injecting link tag for BokehJS stylesheet: \", url);\n document.body.appendChild(element);\n }\n\n for (var i = 0; i < js_urls.length; i++) {\n var url = js_urls[i];\n var element = document.createElement('script');\n element.onload = on_load;\n element.onerror = on_error;\n element.async = false;\n element.src = url;\n console.debug(\"Bokeh: injecting script tag for BokehJS library: \", url);\n document.head.appendChild(element);\n }\n };var element = document.getElementById(\"1001\");\n if (element == null) {\n console.error(\"Bokeh: ERROR: autoload.js configured with elementid '1001' but no matching script tag was found. \")\n return false;\n }\n\n function inject_raw_css(css) {\n const element = document.createElement(\"style\");\n element.appendChild(document.createTextNode(css));\n document.body.appendChild(element);\n }\n\n var js_urls = [\"https://cdn.pydata.org/bokeh/release/bokeh-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-widgets-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-tables-1.3.4.min.js\", \"https://cdn.pydata.org/bokeh/release/bokeh-gl-1.3.4.min.js\"];\n var css_urls = [];\n\n var inline_js = [\n function(Bokeh) {\n Bokeh.set_log_level(\"info\");\n },\n \n function(Bokeh) {\n \n },\n function(Bokeh) {} // ensure no trailing comma for IE\n ];\n\n function run_inline_js() {\n \n if ((root.Bokeh !== undefined) || (force === true)) {\n for (var i = 0; i < inline_js.length; i++) {\n inline_js[i].call(root, root.Bokeh);\n }if (force === true) {\n display_loaded();\n }} else if (Date.now() < root._bokeh_timeout) {\n setTimeout(run_inline_js, 100);\n } else if (!root._bokeh_failed_load) {\n console.log(\"Bokeh: BokehJS failed to load within sLine truncated
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"output_notebook()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You should also adjust all the path constants to point at the relevant locations for you locally"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"MODEL_RUN_PATH = \"/home/neil/main/Projects/TTS3/speaker_encoder/libritts_360-half-September-28-2019_10+46AM-8565c50/\"\n",
|
||||
"MODEL_PATH = MODEL_RUN_PATH + \"best_model.pth.tar\"\n",
|
||||
"CONFIG_PATH = MODEL_RUN_PATH + \"config.json\"\n",
|
||||
"\n",
|
||||
"# My single speaker locations\n",
|
||||
"#EMBED_PATH = \"/home/neil/main/Projects/TTS3/embeddings/neil14/\"\n",
|
||||
"#AUDIO_PATH = \"/home/neil/data/Projects/NeilTTS/neil14/wavs/\"\n",
|
||||
"\n",
|
||||
"# My multi speaker locations\n",
|
||||
"EMBED_PATH = \"/home/neil/main/Projects/TTS3/embeddings/libritts_360/\"\n",
|
||||
"AUDIO_PATH = \"/home/neil/main/Projects/LibriTTS/LibriTTS/train-clean-360/\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"checkpoint_10000.pth.tar config.json\n",
|
||||
"checkpoint_20000.pth.tar events.out.tfevents.1567518806.erogol-desktop\n",
|
||||
"checkpoint_30000.pth.tar\n"
|
||||
"best_model.pth.tar\r\n",
|
||||
"config.json\r\n",
|
||||
"events.out.tfevents.1569660396.erogol-desktop\r\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!ls /media/erogol/data_ssd/Models/libri_tts/speaker_encoder/libritts_360-September-03-2019_03+53PM-dc69074/"
|
||||
"!ls -1 $MODEL_RUN_PATH"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
@@ -29,7 +423,7 @@
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
" > Setting up Audio Processor...\n",
|
||||
" | > sample_rate:16000\n",
|
||||
" | > sample_rate:24000\n",
|
||||
" | > num_mels:40\n",
|
||||
" | > min_level_db:-100\n",
|
||||
" | > frame_shift_ms:12.5\n",
|
||||
@@ -46,61 +440,62 @@
|
||||
" | > max_norm:4.0\n",
|
||||
" | > clip_norm:True\n",
|
||||
" | > do_trim_silence:False\n",
|
||||
" | > sound_norm:False\n",
|
||||
" | > n_fft:2048\n",
|
||||
" | > hop_length:200\n",
|
||||
" | > win_length:800\n"
|
||||
" | > hop_length:300\n",
|
||||
" | > win_length:1200\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import os\n",
|
||||
"import umap\n",
|
||||
"import random\n",
|
||||
"import glob\n",
|
||||
"import numpy as np\n",
|
||||
"\n",
|
||||
"from TTS.speaker_encoder.model import SpeakerEncoder\n",
|
||||
"from TTS.utils.audio import AudioProcessor\n",
|
||||
"from TTS.utils.generic_utils import load_config\n",
|
||||
"\n",
|
||||
"MODEL_PATH = \"/media/erogol/data_ssd/Models/libri_tts/speaker_encoder/libritts_360-half-September-28-2019_10+46AM-8565c50/best_model.pth.tar\"\n",
|
||||
"CONFIG_PATH = \"/media/erogol/data_ssd/Models/libri_tts/speaker_encoder/libritts_360-September-03-2019_03+53PM-dc69074/config.json\"\n",
|
||||
"EMBED_PATH = \"/home/erogol/Data/Libri-TTS/train-clean-360-embed_128/\"\n",
|
||||
"CONFIG = load_config(CONFIG_PATH)\n",
|
||||
"ap = AudioProcessor(**CONFIG['audio'])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Bring in the embeddings created by **compute_embeddings.py**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"116500\n"
|
||||
"Embeddings found: 116500\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"embed_files = glob.glob(EMBED_PATH+\"/**/*.npy\", recursive=True)\n",
|
||||
"print(len(embed_files))"
|
||||
"print(f'Embeddings found: {len(embed_files)}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Check that we did indeed find an embedding"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'/home/erogol/Data/Libri-TTS/train-clean-360-embed_128/1025/75365/1025_75365_000002_000002.npy'"
|
||||
"'/home/neil/main/Projects/TTS3/embeddings/libritts_360/7732/107520/7732_107520_000009_000003.npy'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -109,16 +504,25 @@
|
||||
"embed_files[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Process the speakers\n",
|
||||
"\n",
|
||||
"Assumes count of **speaker_paths** corresponds to number of speakers (so a corpus in just one directory would be treated like a single speaker and the multiple directories of LibriTTS are treated as distinct speakers)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"904\n"
|
||||
"Speaker count: 904\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
@@ -131,19 +535,37 @@
|
||||
" speaker_to_utter[speaker_path].append(embed_file)\n",
|
||||
" except:\n",
|
||||
" speaker_to_utter[speaker_path]=[embed_file]\n",
|
||||
"print(len(speaker_paths))"
|
||||
"print(f'Speaker count: {len(speaker_paths)}')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Set up the embeddings\n",
|
||||
"\n",
|
||||
"Adjust the number of speakers to select and the number of utterances from each speaker and they will be randomly sampled from the corpus"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embeds = []\n",
|
||||
"labels = []\n",
|
||||
"num_speakers = 20\n",
|
||||
"num_utters = 10\n",
|
||||
"locations = []\n",
|
||||
"\n",
|
||||
"# single speaker \n",
|
||||
"#num_speakers = 1\n",
|
||||
"#num_utters = 1000\n",
|
||||
"\n",
|
||||
"# multi speaker\n",
|
||||
"num_speakers = 10\n",
|
||||
"num_utters = 20\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"speaker_idxs = np.random.choice(range(len(speaker_paths)), num_speakers, replace=False )\n",
|
||||
"\n",
|
||||
"for speaker_num, speaker_idx in enumerate(speaker_idxs):\n",
|
||||
@@ -154,69 +576,176 @@
|
||||
" embed_path = speaker_to_utter[speaker_path][utter_idx]\n",
|
||||
" embed = np.load(embed_path)\n",
|
||||
" embeds.append(embed)\n",
|
||||
" labels.append(speaker_num)\n",
|
||||
" labels.append(str(speaker_num))\n",
|
||||
" locations.append(embed_path.replace(EMBED_PATH, '').replace('.npy','.wav'))\n",
|
||||
"embeds = np.concatenate(embeds)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from matplotlib import cm\n",
|
||||
"viridis = cm.get_cmap('tab20', num_speakers)"
|
||||
"Load embeddings with UMAP"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = umap.UMAP()\n",
|
||||
"projection = model.fit_transform(embeds)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Interactively charting the data in Bokeh\n",
|
||||
"\n",
|
||||
"Set up various details for Bokeh to plot the data\n",
|
||||
"\n",
|
||||
"You can use the regular Bokeh [tools](http://docs.bokeh.org/en/1.4.0/docs/user_guide/tools.html?highlight=tools) to explore the data, with reset setting it back to normal\n",
|
||||
"\n",
|
||||
"Once you have started the local server (see cell below) you can then click on plotted points which will open a tab to play the audio for that point, enabling easy exploration of your corpus\n",
|
||||
"\n",
|
||||
"File location in the tooltip is given relative to **AUDIO_PATH**"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/home/erogol/miniconda3/lib/python3.7/site-packages/sklearn/metrics/pairwise.py:258: RuntimeWarning: invalid value encountered in sqrt\n",
|
||||
" return distances if squared else np.sqrt(distances, out=distances)\n",
|
||||
"/home/erogol/miniconda3/lib/python3.7/site-packages/umap/spectral.py:229: UserWarning: Embedding a total of 5 separate connected components using meta-embedding (experimental)\n",
|
||||
" n_components\n"
|
||||
]
|
||||
"data": {
|
||||
"text/html": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
" <div class=\"bk-root\" id=\"e515e894-9f0f-4373-b879-972fbfc359fa\" data-root-id=\"1007\"></div>\n"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"image/png": "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 truncated
|
||||
"text/plain": [
|
||||
"<Figure size 1152x720 with 1 Axes>"
|
||||
]
|
||||
"application/javascript": [
|
||||
"(function(root) {\n",
|
||||
" function embed_document(root) {\n",
|
||||
" \n",
|
||||
" var docs_json = {\"95a95da2-6471-485d-aafc-7fcb3a90c6fa\":{\"roots\":{\"references\":[{\"attributes\":{\"below\":[{\"id\":\"1016\",\"type\":\"LinearAxis\"}],\"center\":[{\"id\":\"1020\",\"type\":\"Grid\"},{\"id\":\"1025\",\"type\":\"Grid\"}],\"left\":[{\"id\":\"1021\",\"type\":\"LinearAxis\"}],\"plot_height\":400,\"renderers\":[{\"id\":\"1035\",\"type\":\"GlyphRenderer\"}],\"title\":{\"id\":\"1038\",\"type\":\"Title\"},\"toolbar\":{\"id\":\"1026\",\"type\":\"Toolbar\"},\"x_range\":{\"id\":\"1008\",\"type\":\"DataRange1d\"},\"x_scale\":{\"id\":\"1012\",\"type\":\"LinearScale\"},\"y_range\":{\"id\":\"1010\",\"type\":\"DataRange1d\"},\"y_scale\":{\"id\":\"1014\",\"type\":\"LinearScale\"}},\"id\":\"1007\",\"subtype\":\"Figure\",\"type\":\"Plot\"},{\"attributes\":{\"source\":{\"id\":\"1002\",\"type\":\"ColumnDataSource\"}},\"id\":\"1036\",\"type\":\"CDSView\"},{\"attributes\":{\"text\":\"\"},\"id\":\"1038\",\"type\":\"Title\"},{\"attributes\":{\"callback\":null},\"id\":\"1008\",\"type\":\"DataRange1d\"},{\"attributes\":{\"url\":\"http://localhost:8000/@desc\"},\"id\":\"1046\",\"type\":\"OpenURL\"},{\"attributes\":{\"callback\":null},\"id\":\"1010\",\"type\":\"DataRange1d\"},{\"attributes\":{},\"id\":\"1045\",\"type\":\"UnionRenderers\"},{\"attributes\":{},\"id\":\"1012\",\"type\":\"LinearScale\"},{\"attributes\":{},\"id\":\"1039\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"active_drag\":\"auto\",\"active_inspect\":\"auto\",\"active_multi\":null,\"active_scroll\":\"auto\",\"active_tap\":\"auto\",\"tools\":[{\"id\":\"1003\",\"type\":\"HoverTool\"},{\"id\":\"1004\",\"type\":\"BoxZoomTool\"},{\"id\":\"1005\",\"type\":\"ResetTool\"},{\"id\":\"1006\",\"type\":\"TapTool\"}]},\"id\":\"1026\",\"type\":\"Toolbar\"},{\"attributes\":{},\"id\":\"1014\",\"type\":\"LinearScale\"},{\"attributes\":{},\"id\":\"1044\",\"type\":\"Selection\"},{\"attributes\":{},\"id\":\"1022\",\"type\":\"BasicTicker\"},{\"attributes\":{\"ticker\":{\"id\":\"1017\",\"type\":\"BasicTicker\"}},\"id\":\"1020\",\"type\":\"Grid\"},{\"attributes\":{\"callback\":{\"id\":\"1046\",\"type\":\"OpenURL\"}},\"id\":\"1006\",\"type\":\"TapTool\"},{\"attributes\":{},\"id\":\"1017\",\"type\":\"BasicTicker\"},{\"attributes\":{\"fill_color\":{\"field\":\"label\",\"transform\":{\"id\":\"1031\",\"type\":\"CategoricalColorMapper\"}},\"line_color\":{\"field\":\"label\",\"transform\":{\"id\":\"1031\",\"type\":\"CategoricalColorMapper\"}},\"x\":{\"field\":\"x\"},\"y\":{\"field\":\"y\"}},\"id\":\"1033\",\"type\":\"Circle\"},{\"attributes\":{\"formatter\":{\"id\":\"1041\",\"type\":\"BasicTickFormatter\"},\"ticker\":{\"id\":\"1017\",\"type\":\"BasicTicker\"}},\"id\":\"1016\",\"type\":\"LinearAxis\"},{\"attributes\":{\"bottom_units\":\"screen\",\"fill_alpha\":{\"value\":0.5},\"fill_color\":{\"value\":\"lightgrey\"},\"left_units\":\"screen\",\"level\":\"overlay\",\"line_alpha\":{\"value\":1.0},\"line_color\":{\"value\":\"black\"},\"line_dash\":[4,4],\"line_width\":{\"value\":2},\"render_mode\":\"css\",\"right_units\":\"screen\",\"top_units\":\"screen\"},\"id\":\"1043\",\"type\":\"BoxAnnotation\"},{\"attributes\":{\"formatter\":{\"id\":\"1039\",\"type\":\"BasicTickFormatter\"},\"ticker\":{\"id\":\"1022\",\"type\":\"BasicTicker\"}},\"id\":\"1021\",\"type\":\"LinearAxis\"},{\"attributes\":{},\"id\":\"1041\",\"type\":\"BasicTickFormatter\"},{\"attributes\":{\"callback\":null,\"tooltips\":[[\"file\",\"@desc\"],[\"speaker\",\"@label\"]]},\"id\":\"1003\",\"type\":\"HoverTool\"},{\"attributes\":{\"callback\":null,\"data\":{\"desc\":[\"8193/116804/8193_116804_000036_000003.wav\",\"8193/116805/8193_116805_000019_000000.wav\",\"8193/116804/8193_116804_000071_000003.wav\",\"8193/116805/8193_116805_000013_000000.wav\",\"8193/116805/8193_116805_000009_000001.wav\",\"8193/116805/8193_116805_000058_000000.wav\",\"8193/116805/8193_116805_000005_000000.wav\",\"8193/116804/8193_116804_000047_000000.wav\",\"8193/116805/8193_116805_000015_000003.wav\",\"8193/116804/8193_116804_000035_000000.wav\",\"8193/116805/8193_116805_000036_000001.wav\",\"8193/116804/8193_116804_000070_000001.wav\",\"8193/116805/8193_116805_000012_000000.wav\",\"8193/116805/8193_116805_000014_000000.wav\",\"8193/116804/8193_116804_000055_000003.wav\",\"8193/116805/8193_116805_000039_000003.wav\",\"8193/116805/8193_116805_000016_000000.wav\",\"8193/116804/8193_116804_000017_000003.wav\",\"8193/116804/8193_116804_000070_000001.wav\",\"8193/116805/8193_116805_000065_000001.wav\",\"829/123192/829_123192_000032_000000.wav\",\"829/123192/829_123192_000059_000000.wav\",\"829/123192/829_123192_000059_000000.wav\",\"829/123191/829_123191_000006_000000.wav\",\"829/123191/829_123191_000053_000001.wav\",\"829/123192/829_123192_000059_000000.wav\",\"829/123192/829_123192_000076_000000.wav\",\"829/123191/829_123191_000077_000003.wav\",\"829/123192/829_123192_000069_000000.wav\",\"829/123192/829_123192_000025_000000.wav\",\"829/123192/829_123192_000011_000000.wav\",\"829/123191/829_123191_000023_000000.wav\",\"829/123192/82Line truncated
|
||||
" var render_items = [{\"docid\":\"95a95da2-6471-485d-aafc-7fcb3a90c6fa\",\"roots\":{\"1007\":\"e515e894-9f0f-4373-b879-972fbfc359fa\"}}];\n",
|
||||
" root.Bokeh.embed.embed_items_notebook(docs_json, render_items);\n",
|
||||
"\n",
|
||||
" }\n",
|
||||
" if (root.Bokeh !== undefined) {\n",
|
||||
" embed_document(root);\n",
|
||||
" } else {\n",
|
||||
" var attempts = 0;\n",
|
||||
" var timer = setInterval(function(root) {\n",
|
||||
" if (root.Bokeh !== undefined) {\n",
|
||||
" embed_document(root);\n",
|
||||
" clearInterval(timer);\n",
|
||||
" }\n",
|
||||
" attempts++;\n",
|
||||
" if (attempts > 100) {\n",
|
||||
" console.log(\"Bokeh: ERROR: Unable to run BokehJS code because BokehJS library is missing\");\n",
|
||||
" clearInterval(timer);\n",
|
||||
" }\n",
|
||||
" }, 10, root)\n",
|
||||
" }\n",
|
||||
"})(window);"
|
||||
],
|
||||
"application/vnd.bokehjs_exec.v0+json": ""
|
||||
},
|
||||
"metadata": {
|
||||
"needs_background": "light"
|
||||
"application/vnd.bokehjs_exec.v0+json": {
|
||||
"id": "1007"
|
||||
}
|
||||
},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from matplotlib import pylab as plt\n",
|
||||
"%matplotlib inline\n",
|
||||
"source_wav_stems = ColumnDataSource(\n",
|
||||
" data=dict(\n",
|
||||
" x = projection.T[0].tolist(),\n",
|
||||
" y = projection.T[1].tolist(),\n",
|
||||
" desc=locations,\n",
|
||||
" label=labels\n",
|
||||
" )\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"model = umap.UMAP()\n",
|
||||
"projection = model.fit_transform(embeds)\n",
|
||||
"colors = [viridis(i) for i in labels]\n",
|
||||
"hover = HoverTool(\n",
|
||||
" tooltips=[\n",
|
||||
" (\"file\", \"@desc\"),\n",
|
||||
" (\"speaker\", \"@label\"),\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
"fig, ax = plt.subplots(figsize=(16, 10))\n",
|
||||
"im = ax.scatter(projection[:, 0], projection[:, 1], c=colors)\n",
|
||||
"plt.gca().set_aspect(\"equal\", \"datalim\")\n",
|
||||
"plt.title(\"UMAP projection\")\n",
|
||||
"plt.tight_layout()"
|
||||
"# optionally consider adding these to the tooltips if you want additional detail\n",
|
||||
"# for the coordinates: (\"(x,y)\", \"($x, $y)\"),\n",
|
||||
"# for the index of the embedding / wav file: (\"index\", \"$index\"),\n",
|
||||
"\n",
|
||||
"factors = list(set(labels))\n",
|
||||
"pal_size = max(len(factors), 3)\n",
|
||||
"pal = Category10[pal_size]\n",
|
||||
"\n",
|
||||
"p = figure(plot_width=600, plot_height=400, tools=[hover,BoxZoomTool(), ResetTool(), TapTool()])\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"p.circle('x', 'y', source=source_wav_stems, color=factor_cmap('label', palette=pal, factors=factors),)\n",
|
||||
"\n",
|
||||
"url = \"http://localhost:8000/@desc\"\n",
|
||||
"taptool = p.select(type=TapTool)\n",
|
||||
"taptool.callback = OpenURL(url=url)\n",
|
||||
"\n",
|
||||
"show(p)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Local server to serve wav files from corpus\n",
|
||||
"\n",
|
||||
"This is required so that when you click on a data point the hyperlink associated with it will be served the file locally.\n",
|
||||
"\n",
|
||||
"There are other ways to serve this if you prefer and you can also run the commands manually on the command line\n",
|
||||
"\n",
|
||||
"The server will continue to run until stopped. To stop it simply interupt the kernel (ie square button or under Kernel menu)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/home/neil/main/Projects/LibriTTS/LibriTTS/train-clean-360\n",
|
||||
"Serving HTTP on 0.0.0.0 port 8000 (http://0.0.0.0:8000/) ...\n",
|
||||
"^C\n",
|
||||
"\n",
|
||||
"Keyboard interrupt received, exiting.\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"%cd $AUDIO_PATH\n",
|
||||
"%pwd\n",
|
||||
"!python -m http.server"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
|
||||
Reference in new issue
Block a user