def change_sample_rate(input_path, new_sample_rate):
"""
Changes the sample rate of a given audio file.
Parameters
----------
input_path : str
Path to audio file
new_sample_rate : int
Sample rate to convert audio to
Returns
-------
str
Path of the converted audio
"""
output_path = add_suffix(input_path, str(new_sample_rate))
check_output(
["ffmpeg", "-i", input_path, "-ar",
str(new_sample_rate), output_path])
return output_path
def create_dataset_post():
min_confidence = float(request.form["confidence"])
language = request.form["language"]
combine_clips = request.form.get("combine_clips") is not None
min_length = float(request.form["min_length"])
max_length = float(request.form["max_length"])
transcription_model = (
Silero(language) if language in SILERO_LANGUAGES else DeepSpeech(
os.path.join(paths["languages"], language, TRANSCRIPTION_MODEL)))
symbols = get_symbols(language)
text_file = SUBTITLE_FILE if request.files["text_file"].filename.endswith(
".srt") else TEXT_FILE
if request.form["name"]:
output_folder = os.path.join(paths["datasets"], request.form["name"])
if os.path.exists(output_folder):
request.files = None
raise Exception("Dataset name taken")
os.makedirs(output_folder, exist_ok=True)
text_path = os.path.join(output_folder, text_file)
audio_path = os.path.join(output_folder,
request.files["audio_file"].filename)
with open(text_path, "w", encoding=CHARACTER_ENCODING) as f:
f.write(request.files["text_file"].read().decode(
CHARACTER_ENCODING, "ignore").replace("\r\n", "\n"))
request.files["audio_file"].save(audio_path)
start_progress_thread(
create_dataset,
text_path=text_path,
audio_path=audio_path,
transcription_model=transcription_model,
output_folder=output_folder,
min_length=min_length,
max_length=max_length,
min_confidence=min_confidence,
combine_clips=combine_clips,
symbols=symbols,
)
else:
output_folder = os.path.join(paths["datasets"],
request.form["dataset"])
suffix = get_suffix()
text_path = os.path.join(output_folder, add_suffix(text_file, suffix))
audio_path = os.path.join(
output_folder,
add_suffix(request.files["audio_file"].filename, suffix))
with open(text_path, "w", encoding=CHARACTER_ENCODING) as f:
f.write(request.files["text_file"].read().decode(
CHARACTER_ENCODING, "ignore").replace("\r\n", "\n"))
request.files["audio_file"].save(audio_path)
start_progress_thread(
extend_existing_dataset,
text_path=text_path,
audio_path=audio_path,
transcription_model=transcription_model,
output_folder=output_folder,
suffix=suffix,
min_length=min_length,
max_length=max_length,
min_confidence=min_confidence,
combine_clips=combine_clips,
symbols=symbols,
)
return render_template("progress.html",
next_url=get_next_url(URLS, request.path))
def extend_existing_dataset(
text_path,
audio_path,
transcription_model,
output_folder,
suffix,
logging=logging,
min_length=MIN_LENGTH,
max_length=MAX_LENGTH,
min_confidence=0.85,
combine_clips=True,
symbols=DEFAULT_ALPHABET,
):
"""
Extends an existing dataset.
Converts audio to required format, generates clips & produces required files.
Parameters
----------
text_path : str
Path to source text
audio_path : str
Path to source audio
transcription_model : TranscriptionModel
Transcription model
output_folder : str
Path to save dataset to
suffix : str
String suffix to append to filenames
logging : logging (optional)
Logging object to write logs to
min_length : float (optional)
Minimum duration of a clip in seconds
max_length : float (optional)
Maximum duration of a clip in seconds
min_confidence : float (optional)
Minimum confidence score to generate a clip for
combine_clips : bool (optional)
Whether to combine clips to make them longer
symbols : list[str] (optional)
list of valid symbols default to DEFAULT_ALPHABET
Raises
-------
AssertionError
If given paths are invalid or clips could not be produced
"""
assert os.path.isdir(
output_folder), "Missing existing dataset clips folder"
logging.info(f"Converting {audio_path}...")
converted_audio = convert_audio(audio_path)
forced_alignment_path = os.path.join(output_folder, ALIGNMENT_FILE)
output_path = os.path.join(output_folder, AUDIO_FOLDER)
unlabelled_path = os.path.join(output_folder, UNLABELLED_FOLDER)
label_path = os.path.join(output_folder, METADATA_FILE)
info_path = os.path.join(output_folder, INFO_FILE)
temp_label_path = label_path.replace(Path(label_path).name, "temp.csv")
temp_unlabelled_folder = unlabelled_path.replace(
Path(unlabelled_path).name, "temp_unlabelled")
temp_wavs_folder = output_path.replace(Path(output_path).name, "temp_wavs")
clip_generator(
converted_audio,
text_path,
transcription_model,
forced_alignment_path,
temp_wavs_folder,
temp_unlabelled_folder,
temp_label_path,
logging=logging,
symbols=symbols,
min_length=min_length,
max_length=max_length,
min_confidence=min_confidence,
combine_clips=combine_clips,
)
with open(temp_label_path) as f:
new_labels = f.readlines()
with open(label_path, "a+") as f:
for line in new_labels:
filename, text = line.split("|")
new_filename = add_suffix(filename, suffix)
f.write(f"{new_filename}|{text}")
for filename in os.listdir(temp_wavs_folder):
new_filename = add_suffix(filename, suffix)
shutil.copyfile(os.path.join(temp_wavs_folder, filename),
os.path.join(output_path, new_filename))
for filename in os.listdir(temp_unlabelled_folder):
new_filename = add_suffix(filename, suffix)
shutil.copyfile(os.path.join(temp_unlabelled_folder, filename),
os.path.join(unlabelled_path, new_filename))
os.remove(temp_label_path)
shutil.rmtree(temp_wavs_folder)
shutil.rmtree(temp_unlabelled_folder)
logging.info("Combined dataset")
logging.info("Getting dataset info...")
# Do not pass clip lengths from extend_dataset as we need to get size of entire dataset (not just new clips)
save_dataset_info(label_path, output_path, info_path)
def test_add_suffix():
new_filename = add_suffix("audio.wav", "converted")
assert new_filename == "audio-converted.wav"