def convert_samplerate(audio_path, desired_sample_rate):
"""Convert extracted audio to the format expected by DeepSpeech
***WONT be called as extract_audio() converts the audio to 16kHz while saving***
Args:
audio_path: audio file path
desired_sample_rate: DeepSpeech expects 16kHz
Returns:
numpy buffer: audio signal stored in numpy array
"""
sox_cmd = "sox {} --type raw --bits 16 --channels 1 --rate {} --encoding signed-integer --endian little --compression 0.0 --no-dither - ".format(
quote(audio_path), desired_sample_rate)
try:
output = subprocess.check_output(shlex.split(sox_cmd),
stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError("SoX returned non-zero status: {}".format(e.stderr))
except OSError as e:
raise OSError(
e.errno, "SoX not found, use {}hz files or install it: {}".format(
desired_sample_rate, e.strerror))
return np.frombuffer(output, np.int16)
def convert_samplerate(audio_path: str, desired_sample_rate: int) -> np.ndarray:
"""
Apply sample rate conversion
# Ref: https://deepspeech.readthedocs.io/en/v0.7.4/Python-Examples.html
"""
sox_cmd: str = """
sox {} --type raw\
--bits 16 --channels 1 --rate {}\
--encoding signed-integer --endian little\
--compression 0.0 --no-dither -
""".format(
quote(audio_path), desired_sample_rate
)
output: bytes = b""
try:
output = subprocess.check_output(shlex.split(sox_cmd), stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError("SoX returned non-zero status: {}".format(e.stderr))
except OSError as e:
raise OSError(
e.errno,
"SoX not found, use {}hz files or install it: {}".format(
desired_sample_rate, e.strerror
),
)
return desired_sample_rate, np.frombuffer(output, np.int16)
def convert_samplerate(audio_path):
sox_cmd = 'sox {} --type raw --bits 16 --channels 1 --rate 16000 - '.format(quote(audio_path))
try:
output = subprocess.check_output(shlex.split(sox_cmd), stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError('SoX returned non-zero status: {}'.format(e.stderr))
except OSError as e:
raise OSError(e.errno, 'SoX not found, use 16kHz files or install it: {}'.format(e.strerror))
return 16000, np.frombuffer(output, np.int16)
def convert_samplerate(audio_path):
sox_cmd = 'sox {} --type raw --bits 16 --channels 1 --rate 16000 - '.format(quote(audio_path))
try:
output = subprocess.check_output(shlex.split(sox_cmd), stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError('SoX returned non-zero status: {}'.format(e.stderr))
except OSError as e:
raise OSError(e.errno, 'SoX not found, use 16kHz files or install it: {}'.format(e.strerror))
return 16000, np.frombuffer(output, np.int16)
def convert_samplerate(audio_path, desired_sample_rate):
sox_cmd = 'sox {} --type raw --bits 16 --channels 1 --rate {} --encoding signed-integer --endian little --compression 0.0 --no-dither - '.format(
quote(audio_path), desired_sample_rate)
try:
output = subprocess.check_output(shlex.split(sox_cmd), stderr=subprocess.PIPE)
except subprocess.CalledProcessError as e:
raise RuntimeError('SoX returned non-zero status: {}'.format(e.stderr))
except OSError as e:
raise OSError(e.errno,
'SoX not found, use {}hz files or install it: {}'.format(desired_sample_rate, e.strerror))
return desired_sample_rate, np.frombuffer(output, np.int16)
def normalize_mp3(mp3filepath):
filename, file_extension = os.path.splitext(mp3filepath)
mp3normfile = "{}{}{}".format(filename, "_norm", file_extension)
normalize_cmd = "ffmpeg-normalize {} ".format(quote(mp3filepath))
normalize_cmd += "-c:a libmp3lame -b:a 192k --normalization-type ebu "
# normalize_cmd += \
# '--loudness-range-target 7.0 --true-peak 0.0 --offset 0.0 '
normalize_cmd += "--target-level {} -f -o {}".format(
NORMALIZE_TARGET_LEVEL, quote(mp3normfile))
if DEBUG:
print(normalize_cmd)
try:
subprocess.check_output(shlex.split(normalize_cmd),
stderr=subprocess.PIPE)
return mp3normfile
except subprocess.CalledProcessError as e:
log.error("ffmpeg-normalize returned non-zero status: {}".format(
e.stderr))
return mp3filepath
except OSError as e:
log.error("ffmpeg-normalize not found {}".format(e.strerror))
return mp3filepath
