Change Hypothesis highlight and WER

.gitignore

@@ -0,0 +1,534 @@
+# generated by: https://github.com/michaelliao/gitignore-online-generator
+
+#################### Python.gitignore ####################
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+#################### Archives.gitignore ####################
+
+# It's better to unpack these files and commit the raw source because
+# git has its own built in compression methods.
+*.7z
+*.jar
+*.rar
+*.zip
+*.gz
+*.gzip
+*.tgz
+*.bzip
+*.bzip2
+*.bz2
+*.xz
+*.lzma
+*.cab
+*.xar
+
+# Packing-only formats
+*.iso
+*.tar
+
+# Package management formats
+*.dmg
+*.xpi
+*.gem
+*.egg
+*.deb
+*.rpm
+*.msi
+*.msm
+*.msp
+*.txz
+
+#################### Backup.gitignore ####################
+
+*.bak
+*.gho
+*.ori
+*.orig
+*.tmp
+
+#################### Emacs.gitignore ####################
+
+# -*- mode: gitignore; -*-
+*~
+\#*\#
+/.emacs.desktop
+/.emacs.desktop.lock
+*.elc
+auto-save-list
+tramp
+.\#*
+
+# Org-mode
+.org-id-locations
+*_archive
+
+# flymake-mode
+*_flymake.*
+
+# eshell files
+/eshell/history
+/eshell/lastdir
+
+# elpa packages
+/elpa/
+
+# reftex files
+*.rel
+
+# AUCTeX auto folder
+/auto/
+
+# cask packages
+.cask/
+dist/
+
+# Flycheck
+flycheck_*.el
+
+# server auth directory
+/server/
+
+# projectiles files
+.projectile
+
+# directory configuration
+.dir-locals.el
+
+# network security
+/network-security.data
+
+
+#################### JetBrains.gitignore ####################
+
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+#################### Linux.gitignore ####################
+
+*~
+
+# temporary files which can be created if a process still has a handle open of a deleted file
+.fuse_hidden*
+
+# KDE directory preferences
+.directory
+
+# Linux trash folder which might appear on any partition or disk
+.Trash-*
+
+# .nfs files are created when an open file is removed but is still being accessed
+.nfs*
+
+#################### NotepadPP.gitignore ####################
+
+# Notepad++ backups #
+*.bak
+
+#################### PuTTY.gitignore ####################
+
+# Private key
+*.ppk
+
+#################### SublimeText.gitignore ####################
+
+# Cache files for Sublime Text
+*.tmlanguage.cache
+*.tmPreferences.cache
+*.stTheme.cache
+
+# Workspace files are user-specific
+*.sublime-workspace
+
+# Project files should be checked into the repository, unless a significant
+# proportion of contributors will probably not be using Sublime Text
+# *.sublime-project
+
+# SFTP configuration file
+sftp-config.json
+sftp-config-alt*.json
+
+# Package control specific files
+Package Control.last-run
+Package Control.ca-list
+Package Control.ca-bundle
+Package Control.system-ca-bundle
+Package Control.cache/
+Package Control.ca-certs/
+Package Control.merged-ca-bundle
+Package Control.user-ca-bundle
+oscrypto-ca-bundle.crt
+bh_unicode_properties.cache
+
+# Sublime-github package stores a github token in this file
+# https://packagecontrol.io/packages/sublime-github
+GitHub.sublime-settings
+
+#################### Vim.gitignore ####################
+
+# Swap
+[._]*.s[a-v][a-z]
+!*.svg  # comment out if you don't need vector files
+[._]*.sw[a-p]
+[._]s[a-rt-v][a-z]
+[._]ss[a-gi-z]
+[._]sw[a-p]
+
+# Session
+Session.vim
+Sessionx.vim
+
+# Temporary
+.netrwhist
+*~
+# Auto-generated tag files
+tags
+# Persistent undo
+[._]*.un~
+
+#################### VirtualEnv.gitignore ####################
+
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+.Python
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+.venv
+pip-selfcheck.json
+
+#################### VisualStudioCode.gitignore ####################
+
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+#################### Windows.gitignore ####################
+
+# Windows thumbnail cache files
+Thumbs.db
+Thumbs.db:encryptable
+ehthumbs.db
+ehthumbs_vista.db
+
+# Dump file
+*.stackdump
+
+# Folder config file
+[Dd]esktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Windows Installer files
+*.cab
+*.msi
+*.msix
+*.msm
+*.msp
+
+# Windows shortcuts
+*.lnk
+
+#################### macOS.gitignore ####################
+
+# General
+.DS_Store
+.AppleDouble
+.LSOverride
+
+# Icon must end with two \r
+Icon
+
+
+# Thumbnails
+._*
+
+# Files that might appear in the root of a volume
+.DocumentRevisions-V100
+.fseventsd
+.Spotlight-V100
+.TemporaryItems
+.Trashes
+.VolumeIcon.icns
+.com.apple.timemachine.donotpresent
+
+# Directories potentially created on remote AFP share
+.AppleDB
+.AppleDesktop
+Network Trash Folder
+Temporary Items
+.apdisk
+
+#################### Custom.gitignore ####################
+
+# add your custom gitignore here:
+!.gitignore
+!.gitsubmodules
+
+# ignore data
+data/
+exp/
+!src/lightning_module.py
+*.wav
+# ignore plots
+*.png
+# ignore csv
+*.csv
+
+
+!config/template.yaml
+config
+!local
+
+## Currently
+src/wav2vec_small.pt
+*.ckpt
+*.bak

app.py

@@ -24,10 +24,12 @@ import librosa.display
 import matplotlib.pyplot as plt
 import soundfile as sf
 
+
 # local import
 import sys
 
 from local.vis import token_plot
+from local.wer import get_WER_highlight
 sys.path.append("src")
 
 # Load automos
@@ -189,6 +191,8 @@ def calc_wer(audio_path, ref):
     trans = jiwer.ToUpperCase()(trans)
     # WER
     ref = jiwer.ToUpperCase()(ref)
+    highlight_hyp = get_WER_highlight(ref.split(" "), trans.split(" "))
+
     wer = jiwer.wer(
         ref,
         trans,
@@ -196,10 +200,12 @@ def calc_wer(audio_path, ref):
         hypothesis_transform=transformation,
     )
     # pdb.set_trace()
-    word_acc = 1.0 - float(wer)
-    return [trans, word_acc, token_wav_plot]
+    word_acc = "%0.2f%%" %((1.0 - float(wer))*100)
+    return [highlight_hyp, word_acc, token_wav_plot]
 # calc_wer(examples[1][0], examples[1][1])
+# # calc_wer()
 # pdb.set_trace()
+
 iface = gr.Interface(
     fn=calc_wer,
     inputs=[
@@ -207,13 +213,15 @@ iface = gr.Interface(
             source="upload",
             type="filepath",
             label="Audio_to_evaluate",
+            show_label=False
         ),
         reference_textbox,
     ],
+    #gr.Textbox(placeholder="Hypothesis", label="Recognition by AI"),
     outputs=[
-        gr.Textbox(placeholder="Hypothesis", label="Recognition by AI"),
+        gr.HighlightedText(placeholder="Hypothesis", label="Diff", combine_adjacent=True, adjacent_separator=" ", show_label=False).style(color_map={"1": "#78bd91", "0": "#ddbabf"}),
         gr.Textbox(placeholder="Word Accuracy", label="Word Accuracy (The Higher the better)"),
-        gr.Plot(label="waveform")
+        gr.Plot(label="waveform", show_label=False)
     ],
     description=description,
     examples=examples,

local/wer.py

@@ -0,0 +1,33 @@
+import Levenshtein
+import numpy as np
+import pdb
+import difflib
+
+ref = "I love you too".split(' ')
+hyp = "I really don't loie him".split(' ')
+
+# return hypothesis wrong word with labels
+def get_WER_highlight(ref, hyp):
+    result = []
+    for li in difflib.ndiff(ref, hyp):
+        if li[0] == "+" or li[0] == " ":
+            x = li.split(" ")
+            # pdb.set_trace()
+            if len(x) == 3:
+                x = (x[-1], "1")
+            else:
+                x = (x[-1], "0")
+            result.append(x)
+    return result            
+
+
+def diff_texts(text1, text2):
+    d = difflib.Differ()
+    return [
+        (token[2:], token[0] if token[0] != " " else None)
+        for token in d.compare(text1, text2)
+    ]
+    
+# x = diff_texts(ref, hyp)
+
+# pdb.set_trace()