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

Python rename

Browse Source
This commit is contained in:
Reuben Morais 2020-08-04 12:12:20 +02:00
parent b86a92a5b3
commit 5449f21a47
3 changed files with 30 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
native_client/python/__init__.py
View File

@ -17,14 +17,14 @@ if platform.system().lower() == "windows":
# directory for the dynamic linker # directory for the dynamic linker
os.environ['PATH'] = dslib_path + ';' + os.environ['PATH'] os.environ['PATH'] = dslib_path + ';' + os.environ['PATH']
import mozilla_voice_stt import mozilla_voice_stt as stt
# rename for backwards compatibility # rename for backwards compatibility
from mozilla_voice_stt.impl import Version as version from stt.impl import Version as version
class Model(object): class Model(object):
""" """
Class holding a DeepSpeech model Class holding a Mozilla Voice STT model
:param aModelPath: Path to model file to load :param aModelPath: Path to model file to load
:type aModelPath: str :type aModelPath: str
@ -33,14 +33,14 @@ class Model(object):
# make sure the attribute is there if CreateModel fails # make sure the attribute is there if CreateModel fails
self._impl = None self._impl = None
status, impl = mozilla_voice_stt.impl.CreateModel(model_path) status, impl = stt.impl.CreateModel(model_path)
if status != 0: if status != 0:
raise RuntimeError("CreateModel failed with '{}' (0x{:X})".format(mozilla_voice_stt.impl.ErrorCodeToErrorMessage(status),status)) raise RuntimeError("CreateModel failed with '{}' (0x{:X})".format(stt.impl.ErrorCodeToErrorMessage(status),status))
self._impl = impl self._impl = impl
def __del__(self): def __del__(self):
if self._impl: if self._impl:
mozilla_voice_stt.impl.FreeModel(self._impl) stt.impl.FreeModel(self._impl)
self._impl = None self._impl = None
def beamWidth(self): def beamWidth(self):
@ -51,7 +51,7 @@ class Model(object):
:return: Beam width value used by the model. :return: Beam width value used by the model.
:type: int :type: int
""" """
return mozilla_voice_stt.impl.GetModelBeamWidth(self._impl) return stt.impl.GetModelBeamWidth(self._impl)
def setBeamWidth(self, beam_width): def setBeamWidth(self, beam_width):
""" """
@ -63,7 +63,7 @@ class Model(object):
:return: Zero on success, non-zero on failure. :return: Zero on success, non-zero on failure.
:type: int :type: int
""" """
return mozilla_voice_stt.impl.SetModelBeamWidth(self._impl, beam_width) return stt.impl.SetModelBeamWidth(self._impl, beam_width)
def sampleRate(self): def sampleRate(self):
""" """
@ -72,7 +72,7 @@ class Model(object):
:return: Sample rate. :return: Sample rate.
:type: int :type: int
""" """
return mozilla_voice_stt.impl.GetModelSampleRate(self._impl) return stt.impl.GetModelSampleRate(self._impl)
def enableExternalScorer(self, scorer_path): def enableExternalScorer(self, scorer_path):
""" """
@ -83,9 +83,9 @@ class Model(object):
:throws: RuntimeError on error :throws: RuntimeError on error
""" """
status = mozilla_voice_stt.impl.EnableExternalScorer(self._impl, scorer_path) status = stt.impl.EnableExternalScorer(self._impl, scorer_path)
if status != 0: if status != 0:
raise RuntimeError("EnableExternalScorer failed with '{}' (0x{:X})".format(mozilla_voice_stt.impl.ErrorCodeToErrorMessage(status),status)) raise RuntimeError("EnableExternalScorer failed with '{}' (0x{:X})".format(stt.impl.ErrorCodeToErrorMessage(status),status))
def disableExternalScorer(self): def disableExternalScorer(self):
""" """
@ -93,7 +93,7 @@ class Model(object):
:return: Zero on success, non-zero on failure. :return: Zero on success, non-zero on failure.
""" """
return mozilla_voice_stt.impl.DisableExternalScorer(self._impl) return stt.impl.DisableExternalScorer(self._impl)
def setScorerAlphaBeta(self, alpha, beta): def setScorerAlphaBeta(self, alpha, beta):
""" """
@ -108,11 +108,11 @@ class Model(object):
:return: Zero on success, non-zero on failure. :return: Zero on success, non-zero on failure.
:type: int :type: int
""" """
return mozilla_voice_stt.impl.SetScorerAlphaBeta(self._impl, alpha, beta) return stt.impl.SetScorerAlphaBeta(self._impl, alpha, beta)
def stt(self, audio_buffer): def stt(self, audio_buffer):
""" """
Use the DeepSpeech model to perform Speech-To-Text. Use the Mozilla Voice STT model to perform Speech-To-Text.
:param audio_buffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on). :param audio_buffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
:type audio_buffer: numpy.int16 array :type audio_buffer: numpy.int16 array
@ -120,11 +120,11 @@ class Model(object):
:return: The STT result. :return: The STT result.
:type: str :type: str
""" """
return mozilla_voice_stt.impl.SpeechToText(self._impl, audio_buffer) return stt.impl.SpeechToText(self._impl, audio_buffer)
def sttWithMetadata(self, audio_buffer, num_results=1): def sttWithMetadata(self, audio_buffer, num_results=1):
""" """
Use the DeepSpeech model to perform Speech-To-Text and return results including metadata. Use the Mozilla Voice STT model to perform Speech-To-Text and return results including metadata.
:param audio_buffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on). :param audio_buffer: A 16-bit, mono raw audio signal at the appropriate sample rate (matching what the model was trained on).
:type audio_buffer: numpy.int16 array :type audio_buffer: numpy.int16 array
@ -135,7 +135,7 @@ class Model(object):
:return: Metadata object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information. :return: Metadata object containing multiple candidate transcripts. Each transcript has per-token metadata including timing information.
:type: :func:`Metadata` :type: :func:`Metadata`
""" """
return mozilla_voice_stt.impl.SpeechToTextWithMetadata(self._impl, audio_buffer, num_results) return stt.impl.SpeechToTextWithMetadata(self._impl, audio_buffer, num_results)
def createStream(self): def createStream(self):
""" """
@ -147,15 +147,15 @@ class Model(object):
:throws: RuntimeError on error :throws: RuntimeError on error
""" """
status, ctx = mozilla_voice_stt.impl.CreateStream(self._impl) status, ctx = stt.impl.CreateStream(self._impl)
if status != 0: if status != 0:
raise RuntimeError("CreateStream failed with '{}' (0x{:X})".format(mozilla_voice_stt.impl.ErrorCodeToErrorMessage(status),status)) raise RuntimeError("CreateStream failed with '{}' (0x{:X})".format(stt.impl.ErrorCodeToErrorMessage(status),status))
return Stream(ctx) return Stream(ctx)
class Stream(object): class Stream(object):
""" """
Class wrapping a DeepSpeech stream. The constructor cannot be called directly. Class wrapping a Mozilla Voice STT stream. The constructor cannot be called directly.
Use :func:`Model.createStream()` Use :func:`Model.createStream()`
""" """
def __init__(self, native_stream): def __init__(self, native_stream):
@ -176,7 +176,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to feed an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to feed an already finished stream?")
mozilla_voice_stt.impl.FeedAudioContent(self._impl, audio_buffer) stt.impl.FeedAudioContent(self._impl, audio_buffer)
def intermediateDecode(self): def intermediateDecode(self):
""" """
@ -189,7 +189,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to decode an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to decode an already finished stream?")
return mozilla_voice_stt.impl.IntermediateDecode(self._impl) return stt.impl.IntermediateDecode(self._impl)
def intermediateDecodeWithMetadata(self, num_results=1): def intermediateDecodeWithMetadata(self, num_results=1):
""" """
@ -205,7 +205,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to decode an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to decode an already finished stream?")
return mozilla_voice_stt.impl.IntermediateDecodeWithMetadata(self._impl, num_results) return stt.impl.IntermediateDecodeWithMetadata(self._impl, num_results)
def finishStream(self): def finishStream(self):
""" """
@ -220,7 +220,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to finish an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to finish an already finished stream?")
result = mozilla_voice_stt.impl.FinishStream(self._impl) result = stt.impl.FinishStream(self._impl)
self._impl = None self._impl = None
return result return result
@ -241,7 +241,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to finish an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to finish an already finished stream?")
result = mozilla_voice_stt.impl.FinishStreamWithMetadata(self._impl, num_results) result = stt.impl.FinishStreamWithMetadata(self._impl, num_results)
self._impl = None self._impl = None
return result return result
@ -254,7 +254,7 @@ class Stream(object):
""" """
if not self._impl: if not self._impl:
raise RuntimeError("Stream object is not valid. Trying to free an already finished stream?") raise RuntimeError("Stream object is not valid. Trying to free an already finished stream?")
mozilla_voice_stt.impl.FreeStream(self._impl) stt.impl.FreeStream(self._impl)
self._impl = None self._impl = None

6
native_client/python/client.py
View File

@ -10,7 +10,7 @@ import sys
import wave import wave
import json import json
from mozilla_voice_stt import Model, version import mozilla_voice_stt as stt
from timeit import default_timer as timer from timeit import default_timer as timer
try: try:
@ -83,7 +83,7 @@ class VersionAction(argparse.Action):
super(VersionAction, self).__init__(nargs=0, *args, **kwargs) super(VersionAction, self).__init__(nargs=0, *args, **kwargs)
def __call__(self, *args, **kwargs): def __call__(self, *args, **kwargs):
print('Mozilla Voice STT ', version()) print('Mozilla Voice STT ', stt.version())
exit(0) exit(0)
@ -114,7 +114,7 @@ def main():
print('Loading model from file {}'.format(args.model), file=sys.stderr) print('Loading model from file {}'.format(args.model), file=sys.stderr)
model_load_start = timer() model_load_start = timer()
# sphinx-doc: python_ref_model_start # sphinx-doc: python_ref_model_start
ds = Model(args.model) ds = stt.Model(args.model)
# sphinx-doc: python_ref_model_stop # sphinx-doc: python_ref_model_stop
model_load_end = timer() - model_load_start model_load_end = timer() - model_load_start
print('Loaded model in {:.3}s.'.format(model_load_end), file=sys.stderr) print('Loaded model in {:.3}s.'.format(model_load_end), file=sys.stderr)

2
native_client/python/setup.py
View File

@ -67,7 +67,7 @@ def main():
swig_opts=['-c++', '-keyword']) swig_opts=['-c++', '-keyword'])
setup(name=project_name, setup(name=project_name,
description='A library for running inference on a DeepSpeech model', description='A library for running inference on a Mozilla Voice STT model',
long_description=read('README.rst'), long_description=read('README.rst'),
long_description_content_type='text/x-rst; charset=UTF-8', long_description_content_type='text/x-rst; charset=UTF-8',
author='Mozilla', author='Mozilla',