Merge pull request #3237 from lissyx/rename-training-package

Rename deepspeech_training package
mozilla · Aug 10, 2020 · 3dcb374 · 3dcb374
2 parents 457198c + 6f84bd1
commit 3dcb374
Show file tree

Hide file tree

Showing 67 changed files with 75 additions and 75 deletions.
diff --git a/DeepSpeech.py b/DeepSpeech.py
@@ -4,7 +4,7 @@
 
 if __name__ == '__main__':
     try:
-        from deepspeech_training import train as ds_train
+        from mozilla_voice_stt_training import train as ds_train
     except ImportError:
         print('Training package is not installed. See training documentation.')
         raise

diff --git a/GRAPH_VERSION b/GRAPH_VERSION
@@ -1 +1 @@
-training/deepspeech_training/GRAPH_VERSION
+training/mozilla_voice_stt_training/GRAPH_VERSION
diff --git a/VERSION b/VERSION
@@ -1 +1 @@
-training/deepspeech_training/VERSION
+training/mozilla_voice_stt_training/VERSION
diff --git a/bin/compare_samples.py b/bin/compare_samples.py
@@ -5,8 +5,8 @@
 import sys
 import argparse
 
-from deepspeech_training.util.audio import AUDIO_TYPE_NP, mean_dbfs
-from deepspeech_training.util.sample_collections import load_sample
+from mozilla_voice_stt_training.util.audio import AUDIO_TYPE_NP, mean_dbfs
+from mozilla_voice_stt_training.util.sample_collections import load_sample
 
 
 def fail(message):

diff --git a/bin/data_set_tool.py b/bin/data_set_tool.py
@@ -8,19 +8,19 @@
 import progressbar
 from pathlib import Path
 
-from deepspeech_training.util.audio import (
+from mozilla_voice_stt_training.util.audio import (
     AUDIO_TYPE_PCM,
     AUDIO_TYPE_OPUS,
     AUDIO_TYPE_WAV,
     change_audio_types,
 )
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.sample_collections import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR
+from mozilla_voice_stt_training.util.sample_collections import (
     CSVWriter,
     DirectSDBWriter,
     samples_from_sources,
 )
-from deepspeech_training.util.augmentations import (
+from mozilla_voice_stt_training.util.augmentations import (
     parse_augmentations,
     apply_sample_augmentations,
     SampleAugmentation

diff --git a/bin/import_aidatatang.py b/bin/import_aidatatang.py
@@ -5,7 +5,7 @@
 
 import pandas
 
-from deepspeech_training.util.importers import get_importers_parser
+from mozilla_voice_stt_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ["wav_filename", "wav_filesize", "transcript"]
 

diff --git a/bin/import_aishell.py b/bin/import_aishell.py
@@ -5,7 +5,7 @@
 
 import pandas
 
-from deepspeech_training.util.importers import get_importers_parser
+from mozilla_voice_stt_training.util.importers import get_importers_parser
 
 COLUMNNAMES = ["wav_filename", "wav_filesize", "transcript"]
 

diff --git a/bin/import_cv.py b/bin/import_cv.py
@@ -9,13 +9,13 @@
 import progressbar
 import sox
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     print_import_report,
 )
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+from mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
 
 FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"]
 SAMPLE_RATE = 16000

diff --git a/bin/import_cv2.py b/bin/import_cv2.py
@@ -15,8 +15,8 @@
 import progressbar
 import sox
 
-from deepspeech_training.util.downloader import SIMPLE_BAR
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     get_importers_parser,

diff --git a/bin/import_fisher.py b/bin/import_fisher.py
@@ -10,7 +10,7 @@
 import pandas
 import soundfile  # <= Has an external dependency on libsndfile
 
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+from mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
 
 # Prerequisite: Having the sph2pipe tool in your PATH:
 # https://www.ldc.upenn.edu/language-resources/tools/sphere-conversion-tools

diff --git a/bin/import_freestmandarin.py b/bin/import_freestmandarin.py
@@ -6,7 +6,7 @@
 import numpy as np
 import pandas
 
-from deepspeech_training.util.importers import get_importers_parser
+from mozilla_voice_stt_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ["wav_filename", "wav_filesize", "transcript"]
 

diff --git a/bin/import_gram_vaani.py b/bin/import_gram_vaani.py
@@ -12,7 +12,7 @@
 from sox import Transformer
 
 import swifter
-from deepspeech_training.util.importers import get_importers_parser, get_validate_label
+from mozilla_voice_stt_training.util.importers import get_importers_parser, get_validate_label
 
 __version__ = "0.1.0"
 _logger = logging.getLogger(__name__)

diff --git a/bin/import_ldc93s1.py b/bin/import_ldc93s1.py
@@ -4,7 +4,7 @@
 
 import pandas
 
-from deepspeech_training.util.downloader import maybe_download
+from mozilla_voice_stt_training.util.downloader import maybe_download
 
 
 def _download_and_preprocess_data(data_dir):

diff --git a/bin/import_librivox.py b/bin/import_librivox.py
@@ -12,7 +12,7 @@
 from sox import Transformer
 from tensorflow.python.platform import gfile
 
-from deepspeech_training.util.downloader import maybe_download
+from mozilla_voice_stt_training.util.downloader import maybe_download
 
 SAMPLE_RATE = 16000
 

diff --git a/bin/import_lingua_libre.py b/bin/import_lingua_libre.py
@@ -12,8 +12,8 @@
 import progressbar
 import sox
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     get_importers_parser,

diff --git a/bin/import_m-ailabs.py b/bin/import_m-ailabs.py
@@ -10,8 +10,8 @@
 
 import progressbar
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     get_importers_parser,

diff --git a/bin/import_magicdata.py b/bin/import_magicdata.py
@@ -6,7 +6,7 @@
 
 import pandas
 
-from deepspeech_training.util.importers import get_importers_parser
+from mozilla_voice_stt_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ["wav_filename", "wav_filesize", "transcript"]
 

diff --git a/bin/import_primewords.py b/bin/import_primewords.py
@@ -7,7 +7,7 @@
 import numpy as np
 import pandas
 
-from deepspeech_training.util.importers import get_importers_parser
+from mozilla_voice_stt_training.util.importers import get_importers_parser
 
 COLUMN_NAMES = ["wav_filename", "wav_filesize", "transcript"]
 

diff --git a/bin/import_slr57.py b/bin/import_slr57.py
@@ -9,8 +9,8 @@
 
 import progressbar
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     get_importers_parser,

diff --git a/bin/import_swb.py b/bin/import_swb.py
@@ -16,7 +16,7 @@
 import requests
 import soundfile  # <= Has an external dependency on libsndfile
 
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+from mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
 
 # ARCHIVE_NAME refers to ISIP alignments from 01/29/03
 ARCHIVE_NAME = "switchboard_word_alignments.tar.gz"

diff --git a/bin/import_swc.py b/bin/import_swc.py
@@ -22,8 +22,8 @@
 import progressbar
 import sox
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
 from ds_ctcdecoder import Alphabet
 
 SWC_URL = "https://www2.informatik.uni-hamburg.de/nats/pub/SWC/SWC_{language}.tar"

diff --git a/bin/import_ted.py b/bin/import_ted.py
@@ -10,8 +10,8 @@
 from sox import Transformer
 from tensorflow.python.platform import gfile
 
-from deepspeech_training.util.downloader import maybe_download
-from deepspeech_training.util.stm import parse_stm_file
+from mozilla_voice_stt_training.util.downloader import maybe_download
+from mozilla_voice_stt_training.util.stm import parse_stm_file
 
 
 def _download_and_preprocess_data(data_dir):

diff --git a/bin/import_ts.py b/bin/import_ts.py
@@ -10,8 +10,8 @@
 import sox
 
 import unidecode
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     get_importers_parser,

diff --git a/bin/import_tuda.py b/bin/import_tuda.py
@@ -14,8 +14,8 @@
 
 import progressbar
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import validate_label_eng as validate_label
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
 from ds_ctcdecoder import Alphabet
 
 TUDA_VERSION = "v2"

diff --git a/bin/import_vctk.py b/bin/import_vctk.py
@@ -11,8 +11,8 @@
 import librosa
 import progressbar
 
-from deepspeech_training.util.downloader import SIMPLE_BAR, maybe_download
-from deepspeech_training.util.importers import (
+from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download
+from mozilla_voice_stt_training.util.importers import (
     get_counter,
     get_imported_samples,
     print_import_report,

diff --git a/bin/import_voxforge.py b/bin/import_voxforge.py
@@ -13,7 +13,7 @@
 import pandas
 from bs4 import BeautifulSoup
 from tensorflow.python.platform import gfile
-from deepspeech_training.util.downloader import maybe_download
+from mozilla_voice_stt_training.util.downloader import maybe_download
 
 """The number of jobs to run in parallel"""
 NUM_PARALLEL = 8

diff --git a/bin/play.py b/bin/play.py
@@ -9,9 +9,9 @@
 import random
 import argparse
 
-from deepspeech_training.util.audio import LOADABLE_AUDIO_EXTENSIONS, AUDIO_TYPE_PCM, AUDIO_TYPE_WAV
-from deepspeech_training.util.sample_collections import SampleList, LabeledSample, samples_from_source
-from deepspeech_training.util.augmentations import parse_augmentations, apply_sample_augmentations, SampleAugmentation
+from mozilla_voice_stt_training.util.audio import LOADABLE_AUDIO_EXTENSIONS, AUDIO_TYPE_PCM, AUDIO_TYPE_WAV
+from mozilla_voice_stt_training.util.sample_collections import SampleList, LabeledSample, samples_from_source
+from mozilla_voice_stt_training.util.augmentations import parse_augmentations, apply_sample_augmentations, SampleAugmentation
 
 
 def get_samples_in_play_order():

diff --git a/data/README.rst b/data/README.rst
@@ -3,7 +3,7 @@ Language-Specific Data
 
 This directory contains language-specific data files. Most importantly, you will find here:
 
-1. A list of unique characters for the target language (e.g. English) in ``data/alphabet.txt``. After installing the training code, you can check ``python -m deepspeech_training.util.check_characters --help`` for a tool that creates an alphabet file from a list of training CSV files.
+1. A list of unique characters for the target language (e.g. English) in ``data/alphabet.txt``. After installing the training code, you can check ``python -m mozilla_voice_stt_training.util.check_characters --help`` for a tool that creates an alphabet file from a list of training CSV files.
 
 2. A script used to generate a binary n-gram language model: ``data/lm/generate_lm.py``.
 

diff --git a/doc/Flags.rst b/doc/Flags.rst
@@ -8,7 +8,7 @@ Below you can find the definition of all command-line flags supported by the tra
 Flags
 -----
 
-.. literalinclude:: ../training/deepspeech_training/util/flags.py
+.. literalinclude:: ../training/mozilla_voice_stt_training/util/flags.py
    :language: python
    :linenos:
    :lineno-match:

diff --git a/doc/examples b/doc/examples
diff --git a/evaluate.py b/evaluate.py
@@ -4,7 +4,7 @@
 
 if __name__ == '__main__':
     try:
-        from deepspeech_training import evaluate as ds_evaluate
+        from mozilla_voice_stt_training import evaluate as ds_evaluate
     except ImportError:
         print('Training package is not installed. See training documentation.')
         raise

diff --git a/evaluate_tflite.py b/evaluate_tflite.py
@@ -11,8 +11,8 @@
 import sys
 
 from mozilla_voice_stt import Model
-from deepspeech_training.util.evaluate_tools import calculate_and_print_report
-from deepspeech_training.util.flags import create_flags
+from mozilla_voice_stt_training.util.evaluate_tools import calculate_and_print_report
+from mozilla_voice_stt_training.util.flags import create_flags
 from functools import partial
 from multiprocessing import JoinableQueue, Process, cpu_count, Manager
 from six.moves import zip, range

diff --git a/lm_optimizer.py b/lm_optimizer.py
@@ -7,12 +7,12 @@
 import sys
 import tensorflow.compat.v1 as tfv1
 
-from deepspeech_training.evaluate import evaluate
-from deepspeech_training.train import create_model
-from deepspeech_training.util.config import Config, initialize_globals
-from deepspeech_training.util.flags import create_flags, FLAGS
-from deepspeech_training.util.logging import log_error
-from deepspeech_training.util.evaluate_tools import wer_cer_batch
+from mozilla_voice_stt_training.evaluate import evaluate
+from mozilla_voice_stt_training.train import create_model
+from mozilla_voice_stt_training.util.config import Config, initialize_globals
+from mozilla_voice_stt_training.util.flags import create_flags, FLAGS
+from mozilla_voice_stt_training.util.logging import log_error
+from mozilla_voice_stt_training.util.evaluate_tools import wer_cer_batch
 from ds_ctcdecoder import Scorer
 
 

diff --git a/native_client/bazel_workspace_status_cmd.sh b/native_client/bazel_workspace_status_cmd.sh
@@ -22,8 +22,8 @@ echo "STABLE_TF_GIT_VERSION ${tf_git_rev}"
 pushd $(dirname "$0")
 ds_git_rev=$(git describe --long --tags)
 echo "STABLE_DS_GIT_VERSION ${ds_git_rev}"
-ds_version=$(cat ../training/deepspeech_training/VERSION)
+ds_version=$(cat ../training/mozilla_voice_stt_training/VERSION)
 echo "STABLE_DS_VERSION ${ds_version}"
-ds_graph_version=$(cat ../training/deepspeech_training/GRAPH_VERSION)
+ds_graph_version=$(cat ../training/mozilla_voice_stt_training/GRAPH_VERSION)
 echo "STABLE_DS_GRAPH_VERSION ${ds_graph_version}"
 popd
diff --git a/native_client/ctcdecode/setup.py b/native_client/ctcdecode/setup.py
@@ -51,7 +51,7 @@ def maybe_rebuild(srcs, out_name, build_dir):
                      num_parallel=known_args.num_processes,
                      debug=debug)
 
-project_version = read('../../training/deepspeech_training/VERSION').strip()
+project_version = read('../../training/mozilla_voice_stt_training/VERSION').strip()
 
 build_dir = 'temp_build/temp_build'
 

diff --git a/native_client/javascript/Makefile b/native_client/javascript/Makefile
@@ -3,7 +3,7 @@ NODE_ABI_TARGET    ?=
 NODE_BUILD_VERBOSE ?= --verbose
 NPM_TOOL           ?= npm
 PROJECT_NAME       ?= @mozilla-voice/stt
-PROJECT_VERSION    ?= $(shell cat ../../training/deepspeech_training/VERSION | tr -d '\n')
+PROJECT_VERSION    ?= $(shell cat ../../training/mozilla_voice_stt_training/VERSION | tr -d '\n')
 NPM_ROOT           ?= $(shell npm root)
 
 NODE_MODULES_BIN   ?= $(NPM_ROOT)/.bin/

diff --git a/native_client/python/setup.py b/native_client/python/setup.py
@@ -31,7 +31,7 @@ def read(fname):
         sys.argv.remove('--project_name')
         sys.argv.pop(project_name_idx)
 
-    with open('../../training/deepspeech_training/VERSION', 'r') as ver:
+    with open('../../training/mozilla_voice_stt_training/VERSION', 'r') as ver:
         project_version = ver.read().strip()
 
     class BuildExtFirst(build):

diff --git a/setup.py b/setup.py
@@ -96,7 +96,7 @@ def main():
         install_requires = install_requires + tensorflow_pypi_dep
 
     setup(
-        name='deepspeech_training',
+        name='mozilla_voice_stt_training',
         version=version,
         description='Training code for mozilla DeepSpeech',
         url='https://github.com/mozilla/DeepSpeech',
@@ -119,7 +119,7 @@ def main():
         # If there are data files included in your packages that need to be
         # installed, specify them here.
         package_data={
-            'deepspeech_training': [
+            'mozilla_voice_stt_training': [
                 'VERSION',
                 'GRAPH_VERSION',
             ],
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		training/deepspeech_training/GRAPH_VERSION
		training/mozilla_voice_stt_training/GRAPH_VERSION
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		training/deepspeech_training/VERSION
		training/mozilla_voice_stt_training/VERSION
+1 −0		README.rst
+4 −5		android_mic_streaming/README.md
+1 −1		android_mic_streaming/app/build.gradle
+10 −10		android_mic_streaming/app/src/main/java/org/deepspeechdemo/MainActivity.kt
+157 −0		batch_processing/Readme.md
+83 −0		batch_processing/driver.py
+61 −0		batch_processing/requirements.txt
+5 −0		batch_processing/setup.ps1
+1 −0		batch_processing/test.ps1
+10 −0		batch_processing/test_tf.py
+95 −0		electron/.gitignore
+71 −0		electron/Readme.md
+16,338 −0		electron/package-lock.json
+98 −0		electron/package.json
+86 −0		electron/public/create-window.js
+22 −0		electron/public/download.js
+24 −0		electron/public/electron.js
+44 −0		electron/public/index.html
+25 −0		electron/public/manifest.json
+2 −0		electron/public/preload.js
+64 −0		electron/public/recognize-wav.js
+60 −0		electron/src/App.js
+5 −0		electron/src/index.js
+36 −0		electron/test.sh
+1 −1		ffmpeg_vad_streaming/README.MD
+1 −1		ffmpeg_vad_streaming/package.json
+6 −6		ffmpeg_vad_streaming/test.sh
+12 −10		mic_vad_streaming/README.rst
+4 −4		mic_vad_streaming/mic_vad_streaming.py
+1 −1		mic_vad_streaming/requirements.txt
+2 −2		mic_vad_streaming/test.sh
+1 −1		net_framework/DeepSpeechWPF/App.xaml.cs
+139 −139		net_framework/DeepSpeechWPF/DeepSpeech.WPF.csproj
+36 −0		nim_mic_vad_streaming/README.md
+70 −0		nim_mic_vad_streaming/linux_nim_vad_streaming/README.md
+190 −0		nim_mic_vad_streaming/linux_nim_vad_streaming/vad_stream.nim
+62 −0		nim_mic_vad_streaming/win_nim_vad_streaming/README.md
+160 −0		nim_mic_vad_streaming/win_nim_vad_streaming/vad_stream.nim
+4 −4		nodejs_mic_vad_streaming/Readme.md
+0 −731		nodejs_mic_vad_streaming/package-lock.json
+1 −1		nodejs_mic_vad_streaming/package.json
+9 −18		nodejs_mic_vad_streaming/start.js
+6 −6		nodejs_wav/Readme.md
+2 −2		nodejs_wav/index.js
+1 −1		nodejs_wav/package.json
+2 −2		tests.sh
+330 −0		uwp/.gitignore
+51 −0		uwp/DeepSpeechUWP.sln
+1 −0		uwp/DeepSpeechUWP/.gitignore
+7 −0		uwp/DeepSpeechUWP/App.xaml
+103 −0		uwp/DeepSpeechUWP/App.xaml.cs
+ −		uwp/DeepSpeechUWP/Assets/LockScreenLogo.scale-200.png
+ −		uwp/DeepSpeechUWP/Assets/SplashScreen.scale-200.png
+ −		uwp/DeepSpeechUWP/Assets/Square150x150Logo.scale-200.png
+ −		uwp/DeepSpeechUWP/Assets/Square44x44Logo.scale-200.png
+ −		uwp/DeepSpeechUWP/Assets/Square44x44Logo.targetsize-24_altform-unplated.png
+ −		uwp/DeepSpeechUWP/Assets/StoreLogo.png
+ −		uwp/DeepSpeechUWP/Assets/Wide310x150Logo.scale-200.png
+190 −0		uwp/DeepSpeechUWP/DeepSpeechUWP.csproj
+51 −0		uwp/DeepSpeechUWP/MainPage.xaml
+328 −0		uwp/DeepSpeechUWP/MainPage.xaml.cs
+50 −0		uwp/DeepSpeechUWP/Package.appxmanifest
+29 −0		uwp/DeepSpeechUWP/Properties/AssemblyInfo.cs
+31 −0		uwp/DeepSpeechUWP/Properties/Default.rd.xml
+0 −0		uwp/DeepSpeechUWP/models/.gitkeep
+0 −0		vad_transcriber/README.md
+1 −1		vad_transcriber/requirements.txt
+4 −4		vad_transcriber/wavTranscriber.py
+2 −2		web_microphone_websocket/Readme.md
+2 −2		web_microphone_websocket/package.json
+9 −18		web_microphone_websocket/server.js
+1 −1		web_microphone_websocket/test.sh
+0 −11,345		web_microphone_websocket/yarn.lock