def split_audio_file(source_audio_file, source_transcript, target_directory):
"""
Execute the split logic
"""
source_audio = audio_file(source_audio_file)
transcript = time_aligned_text(source_transcript)
source_audio.split(transcript, target_directory)
def __init__(self, *args, **kwargs):
"""
Initialize from location and populate list of
SPH, WAV, or MP3 audio files
and STM files into segments
"""
for dictionary in args:
if isinstance(dictionary, dict):
for key in dictionary:
setattr(self, key, dictionary[key])
for key in kwargs:
setattr(self, key, kwargs[key])
# only if not defined above should we search for exemplars
# based on location
if not self.exemplars:
# instantiate exemplars for this object to override
# static class variable
self.exemplars = []
audio_extensions_to_try = ["sph", "wav", "mp3"][::-1]
self.exemplars += [
exemplar({
"audio_file":
audio_file(fl),
"transcript_file":
time_aligned_text(strip_extension(fl) + ".stm"),
}) for audio_extension in audio_extensions_to_try
for fl in (get_files(self.location, audio_extension) if self.
location else [])
if (os.path.exists(strip_extension(fl) + ".stm"))
]
# gather all exemplars from /stm and /sph subdirectories if present
self.exemplars += [
exemplar({
"audio_file":
audio_file(fl),
"transcript_file":
time_aligned_text(self.location + "/stm/" +
basename(strip_extension(fl)) + ".stm"),
}) for audio_extension in audio_extensions_to_try for fl in
(get_files(self.location +
"/sph/", audio_extension) if self.location else [])
if (os.path.exists(self.location + "/stm/" +
basename(strip_extension(fl)) + ".stm"))
]
def split_audio_file(source_audio_file, source_transcript, target_directory):
"""
Split source audio file into segments denoted by transcript file
into target_directory
Results in stm and sph files in target directory
"""
source_audio = audio_file(source_audio_file)
transcript = time_aligned_text(source_transcript)
source_audio.split(transcript, target_directory)
def __init__(self, input_dict=None):
"""
Initialize from location and populate list of SPH and STM files into segments
"""
self.__dict__.update(input_dict if input_dict else {})
if not self.exemplars:
audio_files = [
audio_file(_) for _ in sorted(get_files(self.location, "sph"))
]
transcript_files = [
time_aligned_text(_)
for _ in sorted(get_files(self.location, "stm"))
]
self.exemplars = [
exemplar({
"audio_file": af,
"transcript_file": tf
}) for af, tf in zip(audio_files, transcript_files)
]
def check_audio_file(audio_file_name):
if valid_input_file(audio_file_name, ["mp3", "sph", "wav", "au", "raw"]):
return audio_file(audio_file_name)
else:
LOGGER.error("Invalid audio file {}".format(audio_file_name))
sys.exit(1)