experiments/STT
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #3241 from lissyx/rename-ctcdecoder

Browse Source 
Rename ctcdecoder python package
This commit is contained in:
lissyx 2020-08-11 19:06:56 +02:00 committed by GitHub
commit fd4185f141
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
17 changed files with 23 additions and 23 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
bin/import_cv2.py
View File

@ -23,7 +23,7 @@ from mozilla_voice_stt_training.util.importers import (
get_validate_label, get_validate_label,
print_import_report, print_import_report,
) )
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"] FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"]
SAMPLE_RATE = 16000 SAMPLE_RATE = 16000

2
bin/import_lingua_libre.py
View File

@ -20,7 +20,7 @@ from mozilla_voice_stt_training.util.importers import (
get_validate_label, get_validate_label,
print_import_report, print_import_report,
) )
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"] FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"]
SAMPLE_RATE = 16000 SAMPLE_RATE = 16000

2
bin/import_m-ailabs.py
View File

@ -18,7 +18,7 @@ from mozilla_voice_stt_training.util.importers import (
get_validate_label, get_validate_label,
print_import_report, print_import_report,
) )
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"] FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"]
SAMPLE_RATE = 16000 SAMPLE_RATE = 16000

2
bin/import_slr57.py
View File

@ -17,7 +17,7 @@ from mozilla_voice_stt_training.util.importers import (
get_validate_label, get_validate_label,
print_import_report, print_import_report,
) )
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"] FIELDNAMES = ["wav_filename", "wav_filesize", "transcript"]
SAMPLE_RATE = 16000 SAMPLE_RATE = 16000

2
bin/import_swc.py
View File

@ -24,7 +24,7 @@ import sox
from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download 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 mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
SWC_URL = "https://www2.informatik.uni-hamburg.de/nats/pub/SWC/SWC_{language}.tar" SWC_URL = "https://www2.informatik.uni-hamburg.de/nats/pub/SWC/SWC_{language}.tar"
SWC_ARCHIVE = "SWC_{language}.tar" SWC_ARCHIVE = "SWC_{language}.tar"

2
bin/import_tuda.py
View File

@ -16,7 +16,7 @@ import progressbar
from mozilla_voice_stt_training.util.downloader import SIMPLE_BAR, maybe_download 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 mozilla_voice_stt_training.util.importers import validate_label_eng as validate_label
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
TUDA_VERSION = "v2" TUDA_VERSION = "v2"
TUDA_PACKAGE = "german-speechdata-package-{}".format(TUDA_VERSION) TUDA_PACKAGE = "german-speechdata-package-{}".format(TUDA_VERSION)

2
doc/BUILDING.rst
View File

@ -141,7 +141,7 @@ This will create the package ``mozilla_voice_stt-VERSION.tgz`` in ``native_clien
Install the CTC decoder package Install the CTC decoder package
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
To build the ``ds_ctcdecoder`` package, you'll need the general requirements listed above (in particular SWIG). The command below builds the bindings using eight (8) processes for compilation. Adjust the parameter accordingly for more or less parallelism. To build the ``mvs_ctcdecoder`` package, you'll need the general requirements listed above (in particular SWIG). The command below builds the bindings using eight (8) processes for compilation. Adjust the parameter accordingly for more or less parallelism.
.. code-block:: .. code-block::

2
lm_optimizer.py
View File

@ -13,7 +13,7 @@ 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.flags import create_flags, FLAGS
from mozilla_voice_stt_training.util.logging import log_error from mozilla_voice_stt_training.util.logging import log_error
from mozilla_voice_stt_training.util.evaluate_tools import wer_cer_batch from mozilla_voice_stt_training.util.evaluate_tools import wer_cer_batch
from ds_ctcdecoder import Scorer from mvs_ctcdecoder import Scorer
def character_based(): def character_based():

4
native_client/ctcdecode/Makefile
View File

@ -10,7 +10,7 @@ LDFLAGS_NEEDED += $(RASPBIAN)/lib/aarch64-linux-gnu/libm.so.6
endif endif
ifeq ($(OS),Darwin) ifeq ($(OS),Darwin)
GENERATE_DEBUG_SYMS := dsymutil temp_build/temp_build/ds_ctcdecoder/_swigwrapper.*.so GENERATE_DEBUG_SYMS := dsymutil temp_build/temp_build/mvs_ctcdecoder/_swigwrapper.*.so
else else
GENERATE_DEBUG_SYMS := GENERATE_DEBUG_SYMS :=
endif endif
@ -28,7 +28,7 @@ THIRD_PARTY := third_party.$(ARCHIVE_EXT)
all: bindings all: bindings
clean-keep-third-party: clean-keep-third-party:
rm -rf dist temp_build ds_ctcdecoder.egg-info rm -rf dist temp_build mvs_ctcdecoder.egg-info
rm -f swigwrapper_wrap.cpp swigwrapper.py $(FIRST_PARTY) rm -f swigwrapper_wrap.cpp swigwrapper.py $(FIRST_PARTY)
clean: clean-keep-third-party clean: clean-keep-third-party

8
native_client/ctcdecode/setup.py
View File

@ -68,7 +68,7 @@ maybe_rebuild(KENLM_FILES, third_party_build, build_dir)
maybe_rebuild(CTC_DECODER_FILES, ctc_decoder_build, build_dir) maybe_rebuild(CTC_DECODER_FILES, ctc_decoder_build, build_dir)
decoder_module = Extension( decoder_module = Extension(
name='ds_ctcdecoder._swigwrapper', name='mvs_ctcdecoder._swigwrapper',
sources=['swigwrapper.i'], sources=['swigwrapper.i'],
swig_opts=['-c++', '-extranative'], swig_opts=['-c++', '-extranative'],
language='c++', language='c++',
@ -84,12 +84,12 @@ class BuildExtFirst(build):
('build_scripts', build.has_scripts)] ('build_scripts', build.has_scripts)]
setup( setup(
name='ds_ctcdecoder', name='mvs_ctcdecoder',
version=project_version, version=project_version,
description="""DS CTC decoder""", description="""DS CTC decoder""",
cmdclass = {'build': BuildExtFirst}, cmdclass = {'build': BuildExtFirst},
ext_modules=[decoder_module], ext_modules=[decoder_module],
package_dir = {'ds_ctcdecoder': '.'}, package_dir = {'mvs_ctcdecoder': '.'},
py_modules=['ds_ctcdecoder', 'ds_ctcdecoder.swigwrapper'], py_modules=['mvs_ctcdecoder', 'mvs_ctcdecoder.swigwrapper'],
install_requires = ['numpy%s' % numpy_min_ver], install_requires = ['numpy%s' % numpy_min_ver],
) )

4
setup.py
View File

@ -34,7 +34,7 @@ def get_tc_decoder_pkg_url(version, artifacts_root):
pyver = ''.join(str(i) for i in sys.version_info[0:2]) pyver = ''.join(str(i) for i in sys.version_info[0:2])
return 'ds_ctcdecoder @ {artifacts_root}/ds_ctcdecoder-{ds_version}-cp{pyver}-cp{pyver}{m_or_mu}-{platform}_{arch}.whl'.format( return 'mvs_ctcdecoder @ {artifacts_root}/mvs_ctcdecoder-{ds_version}-cp{pyver}-cp{pyver}{m_or_mu}-{platform}_{arch}.whl'.format(
artifacts_root=artifacts_root, artifacts_root=artifacts_root,
ds_version=ds_version, ds_version=ds_version,
pyver=pyver, pyver=pyver,
@ -70,7 +70,7 @@ def main():
] ]
decoder_pypi_dep = [ decoder_pypi_dep = [
'ds_ctcdecoder == {}'.format(version) 'mvs_ctcdecoder == {}'.format(version)
] ]
tensorflow_pypi_dep = [ tensorflow_pypi_dep = [

2
tests/test_text.py
View File

@ -1,7 +1,7 @@
import unittest import unittest
import os import os
from ds_ctcdecoder import Alphabet from mvs_ctcdecoder import Alphabet
class TestAlphabetParsing(unittest.TestCase): class TestAlphabetParsing(unittest.TestCase):

2
training/mozilla_voice_stt_training/evaluate.py
View File

@ -12,7 +12,7 @@ import progressbar
import tensorflow as tf import tensorflow as tf
import tensorflow.compat.v1 as tfv1 import tensorflow.compat.v1 as tfv1
from ds_ctcdecoder import ctc_beam_search_decoder_batch, Scorer from mvs_ctcdecoder import ctc_beam_search_decoder_batch, Scorer
from six.moves import zip from six.moves import zip
from .util.config import Config, initialize_globals from .util.config import Config, initialize_globals

2
training/mozilla_voice_stt_training/train.py
View File

@ -25,7 +25,7 @@ tfv1.logging.set_verbosity({
}.get(DESIRED_LOG_LEVEL)) }.get(DESIRED_LOG_LEVEL))
from datetime import datetime from datetime import datetime
from ds_ctcdecoder import ctc_beam_search_decoder, Scorer from mvs_ctcdecoder import ctc_beam_search_decoder, Scorer
from .evaluate import evaluate from .evaluate import evaluate
from six.moves import zip, range from six.moves import zip, range
from .util.config import Config, initialize_globals from .util.config import Config, initialize_globals

2
training/mozilla_voice_stt_training/util/config.py
View File

@ -6,7 +6,7 @@ import tensorflow.compat.v1 as tfv1
from attrdict import AttrDict from attrdict import AttrDict
from xdg import BaseDirectory as xdg from xdg import BaseDirectory as xdg
from ds_ctcdecoder import Alphabet, UTF8Alphabet from mvs_ctcdecoder import Alphabet, UTF8Alphabet
from .flags import FLAGS from .flags import FLAGS
from .gpu import get_available_gpus from .gpu import get_available_gpus

4
training/mozilla_voice_stt_training/util/helpers.py
View File

@ -44,11 +44,11 @@ def check_ctcdecoder_version():
try: try:
# pylint: disable=import-outside-toplevel # pylint: disable=import-outside-toplevel
from ds_ctcdecoder import __version__ as decoder_version from mvs_ctcdecoder import __version__ as decoder_version
except ImportError as e: except ImportError as e:
if e.msg.find('__version__') > 0: if e.msg.find('__version__') > 0:
print("Mozilla Voice STT version ({ds_version}) requires CTC decoder to expose __version__. " print("Mozilla Voice STT version ({ds_version}) requires CTC decoder to expose __version__. "
"Please upgrade the ds_ctcdecoder package to version {ds_version}".format(ds_version=ds_version_s)) "Please upgrade the mvs_ctcdecoder package to version {ds_version}".format(ds_version=ds_version_s))
sys.exit(1) sys.exit(1)
raise e raise e

2
transcribe.py
View File

@ -18,7 +18,7 @@ from mozilla_voice_stt_training.util.config import Config, initialize_globals
from mozilla_voice_stt_training.util.feeding import split_audio_file from mozilla_voice_stt_training.util.feeding import split_audio_file
from mozilla_voice_stt_training.util.flags import create_flags, FLAGS from mozilla_voice_stt_training.util.flags import create_flags, FLAGS
from mozilla_voice_stt_training.util.logging import log_error, log_info, log_progress, create_progressbar from mozilla_voice_stt_training.util.logging import log_error, log_info, log_progress, create_progressbar
from ds_ctcdecoder import ctc_beam_search_decoder_batch, Scorer from mvs_ctcdecoder import ctc_beam_search_decoder_batch, Scorer
from multiprocessing import Process, cpu_count from multiprocessing import Process, cpu_count