remove custom_speech_recognition
This commit is contained in:
misyaguziya
File diff suppressed because it is too large
Load Diff
@@ -1,24 +0,0 @@
|
|||||||
import custom_speech_recognition as sr
|
|
||||||
|
|
||||||
r = sr.Recognizer()
|
|
||||||
m = sr.Microphone()
|
|
||||||
|
|
||||||
try:
|
|
||||||
print("A moment of silence, please...")
|
|
||||||
with m as source: r.adjust_for_ambient_noise(source)
|
|
||||||
print("Set minimum energy threshold to {}".format(r.energy_threshold))
|
|
||||||
while True:
|
|
||||||
print("Say something!")
|
|
||||||
with m as source: audio = r.listen(source)
|
|
||||||
print("Got it! Now to recognize it...")
|
|
||||||
try:
|
|
||||||
# recognize speech using Google Speech Recognition
|
|
||||||
value = r.recognize_google(audio)
|
|
||||||
|
|
||||||
print("You said {}".format(value))
|
|
||||||
except sr.UnknownValueError:
|
|
||||||
print("Oops! Didn't catch that")
|
|
||||||
except sr.RequestError as e:
|
|
||||||
print("Uh oh! Couldn't request results from Google Speech Recognition service; {0}".format(e))
|
|
||||||
except KeyboardInterrupt:
|
|
||||||
pass
|
|
||||||
@@ -1,317 +0,0 @@
|
|||||||
import aifc
|
|
||||||
import audioop
|
|
||||||
import io
|
|
||||||
import os
|
|
||||||
import platform
|
|
||||||
import stat
|
|
||||||
import subprocess
|
|
||||||
import sys
|
|
||||||
import wave
|
|
||||||
|
|
||||||
|
|
||||||
class AudioData(object):
|
|
||||||
"""
|
|
||||||
Creates a new ``AudioData`` instance, which represents mono audio data.
|
|
||||||
|
|
||||||
The raw audio data is specified by ``frame_data``, which is a sequence of bytes representing audio samples. This is the frame data structure used by the PCM WAV format.
|
|
||||||
|
|
||||||
The width of each sample, in bytes, is specified by ``sample_width``. Each group of ``sample_width`` bytes represents a single audio sample.
|
|
||||||
|
|
||||||
The audio data is assumed to have a sample rate of ``sample_rate`` samples per second (Hertz).
|
|
||||||
|
|
||||||
Usually, instances of this class are obtained from ``recognizer_instance.record`` or ``recognizer_instance.listen``, or in the callback for ``recognizer_instance.listen_in_background``, rather than instantiating them directly.
|
|
||||||
"""
|
|
||||||
|
|
||||||
def __init__(self, frame_data, sample_rate, sample_width):
|
|
||||||
assert sample_rate > 0, "Sample rate must be a positive integer"
|
|
||||||
assert (
|
|
||||||
sample_width % 1 == 0 and 1 <= sample_width <= 4
|
|
||||||
), "Sample width must be between 1 and 4 inclusive"
|
|
||||||
self.frame_data = frame_data
|
|
||||||
self.sample_rate = sample_rate
|
|
||||||
self.sample_width = int(sample_width)
|
|
||||||
|
|
||||||
def get_segment(self, start_ms=None, end_ms=None):
|
|
||||||
"""
|
|
||||||
Returns a new ``AudioData`` instance, trimmed to a given time interval. In other words, an ``AudioData`` instance with the same audio data except starting at ``start_ms`` milliseconds in and ending ``end_ms`` milliseconds in.
|
|
||||||
|
|
||||||
If not specified, ``start_ms`` defaults to the beginning of the audio, and ``end_ms`` defaults to the end.
|
|
||||||
"""
|
|
||||||
assert (
|
|
||||||
start_ms is None or start_ms >= 0
|
|
||||||
), "``start_ms`` must be a non-negative number"
|
|
||||||
assert end_ms is None or end_ms >= (
|
|
||||||
0 if start_ms is None else start_ms
|
|
||||||
), "``end_ms`` must be a non-negative number greater or equal to ``start_ms``"
|
|
||||||
if start_ms is None:
|
|
||||||
start_byte = 0
|
|
||||||
else:
|
|
||||||
start_byte = int(
|
|
||||||
(start_ms * self.sample_rate * self.sample_width) // 1000
|
|
||||||
)
|
|
||||||
if end_ms is None:
|
|
||||||
end_byte = len(self.frame_data)
|
|
||||||
else:
|
|
||||||
end_byte = int(
|
|
||||||
(end_ms * self.sample_rate * self.sample_width) // 1000
|
|
||||||
)
|
|
||||||
return AudioData(
|
|
||||||
self.frame_data[start_byte:end_byte],
|
|
||||||
self.sample_rate,
|
|
||||||
self.sample_width,
|
|
||||||
)
|
|
||||||
|
|
||||||
def get_raw_data(self, convert_rate=None, convert_width=None):
|
|
||||||
"""
|
|
||||||
Returns a byte string representing the raw frame data for the audio represented by the ``AudioData`` instance.
|
|
||||||
|
|
||||||
If ``convert_rate`` is specified and the audio sample rate is not ``convert_rate`` Hz, the resulting audio is resampled to match.
|
|
||||||
|
|
||||||
If ``convert_width`` is specified and the audio samples are not ``convert_width`` bytes each, the resulting audio is converted to match.
|
|
||||||
|
|
||||||
Writing these bytes directly to a file results in a valid `RAW/PCM audio file <https://en.wikipedia.org/wiki/Raw_audio_format>`__.
|
|
||||||
"""
|
|
||||||
assert (
|
|
||||||
convert_rate is None or convert_rate > 0
|
|
||||||
), "Sample rate to convert to must be a positive integer"
|
|
||||||
assert convert_width is None or (
|
|
||||||
convert_width % 1 == 0 and 1 <= convert_width <= 4
|
|
||||||
), "Sample width to convert to must be between 1 and 4 inclusive"
|
|
||||||
|
|
||||||
raw_data = self.frame_data
|
|
||||||
|
|
||||||
# make sure unsigned 8-bit audio (which uses unsigned samples) is handled like higher sample width audio (which uses signed samples)
|
|
||||||
if self.sample_width == 1:
|
|
||||||
raw_data = audioop.bias(
|
|
||||||
raw_data, 1, -128
|
|
||||||
) # subtract 128 from every sample to make them act like signed samples
|
|
||||||
|
|
||||||
# resample audio at the desired rate if specified
|
|
||||||
if convert_rate is not None and self.sample_rate != convert_rate:
|
|
||||||
raw_data, _ = audioop.ratecv(
|
|
||||||
raw_data,
|
|
||||||
self.sample_width,
|
|
||||||
1,
|
|
||||||
self.sample_rate,
|
|
||||||
convert_rate,
|
|
||||||
None,
|
|
||||||
)
|
|
||||||
|
|
||||||
# convert samples to desired sample width if specified
|
|
||||||
if convert_width is not None and self.sample_width != convert_width:
|
|
||||||
if (
|
|
||||||
convert_width == 3
|
|
||||||
): # we're converting the audio into 24-bit (workaround for https://bugs.python.org/issue12866)
|
|
||||||
raw_data = audioop.lin2lin(
|
|
||||||
raw_data, self.sample_width, 4
|
|
||||||
) # convert audio into 32-bit first, which is always supported
|
|
||||||
try:
|
|
||||||
audioop.bias(
|
|
||||||
b"", 3, 0
|
|
||||||
) # test whether 24-bit audio is supported (for example, ``audioop`` in Python 3.3 and below don't support sample width 3, while Python 3.4+ do)
|
|
||||||
except (
|
|
||||||
audioop.error
|
|
||||||
): # this version of audioop doesn't support 24-bit audio (probably Python 3.3 or less)
|
|
||||||
raw_data = b"".join(
|
|
||||||
raw_data[i + 1 : i + 4]
|
|
||||||
for i in range(0, len(raw_data), 4)
|
|
||||||
) # since we're in little endian, we discard the first byte from each 32-bit sample to get a 24-bit sample
|
|
||||||
else: # 24-bit audio fully supported, we don't need to shim anything
|
|
||||||
raw_data = audioop.lin2lin(
|
|
||||||
raw_data, self.sample_width, convert_width
|
|
||||||
)
|
|
||||||
else:
|
|
||||||
raw_data = audioop.lin2lin(
|
|
||||||
raw_data, self.sample_width, convert_width
|
|
||||||
)
|
|
||||||
|
|
||||||
# if the output is 8-bit audio with unsigned samples, convert the samples we've been treating as signed to unsigned again
|
|
||||||
if convert_width == 1:
|
|
||||||
raw_data = audioop.bias(
|
|
||||||
raw_data, 1, 128
|
|
||||||
) # add 128 to every sample to make them act like unsigned samples again
|
|
||||||
|
|
||||||
return raw_data
|
|
||||||
|
|
||||||
def get_wav_data(self, convert_rate=None, convert_width=None, nchannels = 1):
|
|
||||||
"""
|
|
||||||
Returns a byte string representing the contents of a WAV file containing the audio represented by the ``AudioData`` instance.
|
|
||||||
|
|
||||||
If ``convert_width`` is specified and the audio samples are not ``convert_width`` bytes each, the resulting audio is converted to match.
|
|
||||||
|
|
||||||
If ``convert_rate`` is specified and the audio sample rate is not ``convert_rate`` Hz, the resulting audio is resampled to match.
|
|
||||||
|
|
||||||
Writing these bytes directly to a file results in a valid `WAV file <https://en.wikipedia.org/wiki/WAV>`__.
|
|
||||||
"""
|
|
||||||
raw_data = self.get_raw_data(convert_rate, convert_width)
|
|
||||||
sample_rate = (
|
|
||||||
self.sample_rate if convert_rate is None else convert_rate
|
|
||||||
)
|
|
||||||
sample_width = (
|
|
||||||
self.sample_width if convert_width is None else convert_width
|
|
||||||
)
|
|
||||||
|
|
||||||
# generate the WAV file contents
|
|
||||||
with io.BytesIO() as wav_file:
|
|
||||||
wav_writer = wave.open(wav_file, "wb")
|
|
||||||
try: # note that we can't use context manager, since that was only added in Python 3.4
|
|
||||||
wav_writer.setframerate(sample_rate)
|
|
||||||
wav_writer.setsampwidth(sample_width)
|
|
||||||
wav_writer.setnchannels(nchannels)
|
|
||||||
wav_writer.writeframes(raw_data)
|
|
||||||
wav_data = wav_file.getvalue()
|
|
||||||
finally: # make sure resources are cleaned up
|
|
||||||
wav_writer.close()
|
|
||||||
return wav_data
|
|
||||||
|
|
||||||
def get_aiff_data(self, convert_rate=None, convert_width=None):
|
|
||||||
"""
|
|
||||||
Returns a byte string representing the contents of an AIFF-C file containing the audio represented by the ``AudioData`` instance.
|
|
||||||
|
|
||||||
If ``convert_width`` is specified and the audio samples are not ``convert_width`` bytes each, the resulting audio is converted to match.
|
|
||||||
|
|
||||||
If ``convert_rate`` is specified and the audio sample rate is not ``convert_rate`` Hz, the resulting audio is resampled to match.
|
|
||||||
|
|
||||||
Writing these bytes directly to a file results in a valid `AIFF-C file <https://en.wikipedia.org/wiki/Audio_Interchange_File_Format>`__.
|
|
||||||
"""
|
|
||||||
raw_data = self.get_raw_data(convert_rate, convert_width)
|
|
||||||
sample_rate = (
|
|
||||||
self.sample_rate if convert_rate is None else convert_rate
|
|
||||||
)
|
|
||||||
sample_width = (
|
|
||||||
self.sample_width if convert_width is None else convert_width
|
|
||||||
)
|
|
||||||
|
|
||||||
# the AIFF format is big-endian, so we need to convert the little-endian raw data to big-endian
|
|
||||||
if hasattr(
|
|
||||||
audioop, "byteswap"
|
|
||||||
): # ``audioop.byteswap`` was only added in Python 3.4
|
|
||||||
raw_data = audioop.byteswap(raw_data, sample_width)
|
|
||||||
else: # manually reverse the bytes of each sample, which is slower but works well enough as a fallback
|
|
||||||
raw_data = raw_data[sample_width - 1 :: -1] + b"".join(
|
|
||||||
raw_data[i + sample_width : i : -1]
|
|
||||||
for i in range(sample_width - 1, len(raw_data), sample_width)
|
|
||||||
)
|
|
||||||
|
|
||||||
# generate the AIFF-C file contents
|
|
||||||
with io.BytesIO() as aiff_file:
|
|
||||||
aiff_writer = aifc.open(aiff_file, "wb")
|
|
||||||
try: # note that we can't use context manager, since that was only added in Python 3.4
|
|
||||||
aiff_writer.setframerate(sample_rate)
|
|
||||||
aiff_writer.setsampwidth(sample_width)
|
|
||||||
aiff_writer.setnchannels(1)
|
|
||||||
aiff_writer.writeframes(raw_data)
|
|
||||||
aiff_data = aiff_file.getvalue()
|
|
||||||
finally: # make sure resources are cleaned up
|
|
||||||
aiff_writer.close()
|
|
||||||
return aiff_data
|
|
||||||
|
|
||||||
def get_flac_data(self, convert_rate=None, convert_width=None):
|
|
||||||
"""
|
|
||||||
Returns a byte string representing the contents of a FLAC file containing the audio represented by the ``AudioData`` instance.
|
|
||||||
|
|
||||||
Note that 32-bit FLAC is not supported. If the audio data is 32-bit and ``convert_width`` is not specified, then the resulting FLAC will be a 24-bit FLAC.
|
|
||||||
|
|
||||||
If ``convert_rate`` is specified and the audio sample rate is not ``convert_rate`` Hz, the resulting audio is resampled to match.
|
|
||||||
|
|
||||||
If ``convert_width`` is specified and the audio samples are not ``convert_width`` bytes each, the resulting audio is converted to match.
|
|
||||||
|
|
||||||
Writing these bytes directly to a file results in a valid `FLAC file <https://en.wikipedia.org/wiki/FLAC>`__.
|
|
||||||
"""
|
|
||||||
assert convert_width is None or (
|
|
||||||
convert_width % 1 == 0 and 1 <= convert_width <= 3
|
|
||||||
), "Sample width to convert to must be between 1 and 3 inclusive"
|
|
||||||
|
|
||||||
if (
|
|
||||||
self.sample_width > 3 and convert_width is None
|
|
||||||
): # resulting WAV data would be 32-bit, which is not convertable to FLAC using our encoder
|
|
||||||
convert_width = 3 # the largest supported sample width is 24-bit, so we'll limit the sample width to that
|
|
||||||
|
|
||||||
# run the FLAC converter with the WAV data to get the FLAC data
|
|
||||||
wav_data = self.get_wav_data(convert_rate, convert_width)
|
|
||||||
flac_converter = get_flac_converter()
|
|
||||||
if (
|
|
||||||
os.name == "nt"
|
|
||||||
): # on Windows, specify that the process is to be started without showing a console window
|
|
||||||
startup_info = subprocess.STARTUPINFO()
|
|
||||||
startup_info.dwFlags |= (
|
|
||||||
subprocess.STARTF_USESHOWWINDOW
|
|
||||||
) # specify that the wShowWindow field of `startup_info` contains a value
|
|
||||||
startup_info.wShowWindow = (
|
|
||||||
subprocess.SW_HIDE
|
|
||||||
) # specify that the console window should be hidden
|
|
||||||
else:
|
|
||||||
startup_info = None # default startupinfo
|
|
||||||
process = subprocess.Popen(
|
|
||||||
[
|
|
||||||
flac_converter,
|
|
||||||
"--stdout",
|
|
||||||
"--totally-silent", # put the resulting FLAC file in stdout, and make sure it's not mixed with any program output
|
|
||||||
"--best", # highest level of compression available
|
|
||||||
"-", # the input FLAC file contents will be given in stdin
|
|
||||||
],
|
|
||||||
stdin=subprocess.PIPE,
|
|
||||||
stdout=subprocess.PIPE,
|
|
||||||
startupinfo=startup_info,
|
|
||||||
)
|
|
||||||
flac_data, stderr = process.communicate(wav_data)
|
|
||||||
return flac_data
|
|
||||||
|
|
||||||
|
|
||||||
def get_flac_converter():
|
|
||||||
"""Returns the absolute path of a FLAC converter executable, or raises an OSError if none can be found."""
|
|
||||||
flac_converter = shutil_which("flac") # check for installed version first
|
|
||||||
if flac_converter is None: # flac utility is not installed
|
|
||||||
base_path = os.path.dirname(
|
|
||||||
os.path.abspath(__file__)
|
|
||||||
) # directory of the current module file, where all the FLAC bundled binaries are stored
|
|
||||||
system, machine = platform.system(), platform.machine()
|
|
||||||
if system == "Windows" and machine in {
|
|
||||||
"i686",
|
|
||||||
"i786",
|
|
||||||
"x86",
|
|
||||||
"x86_64",
|
|
||||||
"AMD64",
|
|
||||||
}:
|
|
||||||
flac_converter = os.path.join(base_path, "flac-win32.exe")
|
|
||||||
elif system == "Darwin" and machine in {
|
|
||||||
"i686",
|
|
||||||
"i786",
|
|
||||||
"x86",
|
|
||||||
"x86_64",
|
|
||||||
"AMD64",
|
|
||||||
}:
|
|
||||||
flac_converter = os.path.join(base_path, "flac-mac")
|
|
||||||
elif system == "Linux" and machine in {"i686", "i786", "x86"}:
|
|
||||||
flac_converter = os.path.join(base_path, "flac-linux-x86")
|
|
||||||
elif system == "Linux" and machine in {"x86_64", "AMD64"}:
|
|
||||||
flac_converter = os.path.join(base_path, "flac-linux-x86_64")
|
|
||||||
else: # no FLAC converter available
|
|
||||||
raise OSError(
|
|
||||||
"FLAC conversion utility not available - consider installing the FLAC command line application by running `apt-get install flac` or your operating system's equivalent"
|
|
||||||
)
|
|
||||||
|
|
||||||
# mark FLAC converter as executable if possible
|
|
||||||
try:
|
|
||||||
# handle known issue when running on docker:
|
|
||||||
# run executable right after chmod() may result in OSError "Text file busy"
|
|
||||||
# fix: flush FS with sync
|
|
||||||
if not os.access(flac_converter, os.X_OK):
|
|
||||||
stat_info = os.stat(flac_converter)
|
|
||||||
os.chmod(flac_converter, stat_info.st_mode | stat.S_IEXEC)
|
|
||||||
if "Linux" in platform.system():
|
|
||||||
os.sync() if sys.version_info >= (3, 3) else os.system("sync")
|
|
||||||
|
|
||||||
except OSError:
|
|
||||||
pass
|
|
||||||
|
|
||||||
return flac_converter
|
|
||||||
|
|
||||||
|
|
||||||
def shutil_which(pgm):
|
|
||||||
"""Python 2 compatibility: backport of ``shutil.which()`` from Python 3"""
|
|
||||||
path = os.getenv("PATH")
|
|
||||||
for p in path.split(os.path.pathsep):
|
|
||||||
p = os.path.join(p, pgm)
|
|
||||||
if os.path.exists(p) and os.access(p, os.X_OK):
|
|
||||||
return p
|
|
||||||
@@ -1,22 +0,0 @@
|
|||||||
class SetupError(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class WaitTimeoutError(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class RequestError(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class UnknownValueError(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class TranscriptionNotReady(Exception):
|
|
||||||
pass
|
|
||||||
|
|
||||||
|
|
||||||
class TranscriptionFailed(Exception):
|
|
||||||
pass
|
|
||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
@@ -1,31 +0,0 @@
|
|||||||
Copyright (c) 1999-2015 Carnegie Mellon University. All rights
|
|
||||||
reserved.
|
|
||||||
|
|
||||||
Redistribution and use in source and binary forms, with or without
|
|
||||||
modification, are permitted provided that the following conditions
|
|
||||||
are met:
|
|
||||||
|
|
||||||
1. Redistributions of source code must retain the above copyright
|
|
||||||
notice, this list of conditions and the following disclaimer.
|
|
||||||
|
|
||||||
2. Redistributions in binary form must reproduce the above copyright
|
|
||||||
notice, this list of conditions and the following disclaimer in
|
|
||||||
the documentation and/or other materials provided with the
|
|
||||||
distribution.
|
|
||||||
|
|
||||||
This work was supported in part by funding from the Defense Advanced
|
|
||||||
Research Projects Agency and the National Science Foundation of the
|
|
||||||
United States of America, and the CMU Sphinx Speech Consortium.
|
|
||||||
|
|
||||||
THIS SOFTWARE IS PROVIDED BY CARNEGIE MELLON UNIVERSITY ``AS IS'' AND
|
|
||||||
ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,
|
|
||||||
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
|
||||||
PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL CARNEGIE MELLON UNIVERSITY
|
|
||||||
NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
||||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
|
||||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
|
||||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
|
||||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
|
||||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
||||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
||||||
|
|
||||||
@@ -1,34 +0,0 @@
|
|||||||
/* ====================================================================
|
|
||||||
* Copyright (c) 2015 Alpha Cephei Inc. All rights
|
|
||||||
* reserved.
|
|
||||||
*
|
|
||||||
* Redistribution and use in source and binary forms, with or without
|
|
||||||
* modification, are permitted provided that the following conditions
|
|
||||||
* are met:
|
|
||||||
*
|
|
||||||
* 1. Redistributions of source code must retain the above copyright
|
|
||||||
* notice, this list of conditions and the following disclaimer.
|
|
||||||
*
|
|
||||||
* 2. Redistributions in binary form must reproduce the above copyright
|
|
||||||
* notice, this list of conditions and the following disclaimer in
|
|
||||||
* the documentation and/or other materials provided with the
|
|
||||||
* distribution.
|
|
||||||
*
|
|
||||||
* THIS SOFTWARE IS PROVIDED BY ALPHA CEPHEI INC. ``AS IS'' AND.
|
|
||||||
* ANY EXPRESSED OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,.
|
|
||||||
* THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
|
|
||||||
* PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL ALPHA CEPHEI INC.
|
|
||||||
* NOR ITS EMPLOYEES BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
|
||||||
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT.
|
|
||||||
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,.
|
|
||||||
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY.
|
|
||||||
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT.
|
|
||||||
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE.
|
|
||||||
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
||||||
*
|
|
||||||
* ====================================================================
|
|
||||||
*
|
|
||||||
*/
|
|
||||||
|
|
||||||
This directory contains generic US english acoustic model trained with
|
|
||||||
latest sphinxtrain.
|
|
||||||
@@ -1,12 +0,0 @@
|
|||||||
-lowerf 130
|
|
||||||
-upperf 6800
|
|
||||||
-nfilt 25
|
|
||||||
-transform dct
|
|
||||||
-lifter 22
|
|
||||||
-feat 1s_c_d_dd
|
|
||||||
-svspec 0-12/13-25/26-38
|
|
||||||
-agc none
|
|
||||||
-cmn current
|
|
||||||
-varnorm no
|
|
||||||
-model ptm
|
|
||||||
-cmninit 40,3,-1
|
|
||||||
Binary file not shown.
|
Before Width: | Height: | Size: 2.8 MiB |
Binary file not shown.
@@ -1,5 +0,0 @@
|
|||||||
<s> SIL
|
|
||||||
</s> SIL
|
|
||||||
<sil> SIL
|
|
||||||
[NOISE] +NSN+
|
|
||||||
[SPEECH] +SPN+
|
|
||||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
File diff suppressed because it is too large
Load Diff
@@ -1,42 +0,0 @@
|
|||||||
from __future__ import annotations
|
|
||||||
|
|
||||||
import os
|
|
||||||
from io import BytesIO
|
|
||||||
|
|
||||||
from custom_speech_recognition.audio import AudioData
|
|
||||||
from custom_speech_recognition.exceptions import SetupError
|
|
||||||
|
|
||||||
|
|
||||||
def recognize_whisper_api(
|
|
||||||
recognizer,
|
|
||||||
audio_data: "AudioData",
|
|
||||||
*,
|
|
||||||
model: str = "whisper-1",
|
|
||||||
api_key: str | None = None,
|
|
||||||
):
|
|
||||||
"""
|
|
||||||
Performs speech recognition on ``audio_data`` (an ``AudioData`` instance), using the OpenAI Whisper API.
|
|
||||||
|
|
||||||
This function requires an OpenAI account; visit https://platform.openai.com/signup, then generate API Key in `User settings <https://platform.openai.com/account/api-keys>`__.
|
|
||||||
|
|
||||||
Detail: https://platform.openai.com/docs/guides/speech-to-text
|
|
||||||
|
|
||||||
Raises a ``speech_recognition.exceptions.SetupError`` exception if there are any issues with the openai installation, or the environment variable is missing.
|
|
||||||
"""
|
|
||||||
if not isinstance(audio_data, AudioData):
|
|
||||||
raise ValueError("``audio_data`` must be an ``AudioData`` instance")
|
|
||||||
if api_key is None and os.environ.get("OPENAI_API_KEY") is None:
|
|
||||||
raise SetupError("Set environment variable ``OPENAI_API_KEY``")
|
|
||||||
|
|
||||||
try:
|
|
||||||
import openai
|
|
||||||
except ImportError:
|
|
||||||
raise SetupError(
|
|
||||||
"missing openai module: ensure that openai is set up correctly."
|
|
||||||
)
|
|
||||||
|
|
||||||
wav_data = BytesIO(audio_data.get_wav_data())
|
|
||||||
wav_data.name = "SpeechRecognition_audio.wav"
|
|
||||||
|
|
||||||
transcript = openai.Audio.transcribe(model, wav_data, api_key=api_key)
|
|
||||||
return transcript["text"]
|
|
||||||
Reference in New Issue
Block a user