def synthesis_post():
global model, waveglow_model
if not model:
return redirect("/synthesis-setup")
if request.method == "GET":
return render_template("synthesis.html")
else:
text = request.form["text"]
folder_name = get_suffix()
results_folder = os.path.join(paths["results"], folder_name)
os.makedirs(results_folder)
graph_path = os.path.join(results_folder, GRAPH_FILE)
audio_path = os.path.join(results_folder, RESULTS_FILE)
graph_web_path = graph_path.replace("\\", "/")
audio_web_path = audio_path.replace("\\", "/")
synthesize(model, waveglow_model, text, inflect_engine, graph_path,
audio_path)
return render_template(
"synthesis.html",
text=text.strip(),
alertnative_words=get_alternative_word_suggestions(
audio_path, text),
graph=graph_web_path,
audio=audio_web_path,
)
def create_dataset_post():
min_confidence = request.form["confidence"]
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, AUDIO_FILE)
forced_alignment_path = os.path.join(output_folder, ALIGNMENT_FILE)
output_path = os.path.join(output_folder, AUDIO_FOLDER)
label_path = os.path.join(output_folder, METADATA_FILE)
info_path = os.path.join(output_folder, INFO_FILE)
request.files["text_file"].save(text_path)
request.files["audio_file"].save(audio_path)
start_progress_thread(
create_dataset,
text_path=text_path,
audio_path=audio_path,
forced_alignment_path=forced_alignment_path,
output_path=output_path,
label_path=label_path,
info_path=info_path,
min_confidence=float(min_confidence),
)
else:
output_folder = os.path.join(paths["datasets"], request.form["path"])
suffix = get_suffix()
text_path = os.path.join(output_folder, f"text-{suffix}.txt")
audio_path = os.path.join(output_folder, f"audio-{suffix}.mp3")
forced_alignment_path = os.path.join(output_folder,
f"align-{suffix}.json")
info_path = os.path.join(output_folder, INFO_FILE)
request.files["text_file"].save(text_path)
request.files["audio_file"].save(audio_path)
existing_output_path = os.path.join(output_folder, AUDIO_FOLDER)
existing_label_path = os.path.join(output_folder, METADATA_FILE)
start_progress_thread(
extend_existing_dataset,
text_path=text_path,
audio_path=audio_path,
forced_alignment_path=forced_alignment_path,
output_path=existing_output_path,
label_path=existing_label_path,
suffix=suffix,
info_path=info_path,
min_confidence=float(min_confidence),
)
return render_template("progress.html",
next_url=get_next_url(URLS, request.path))
def synthesis_post():
global model, vocoder, symbols
if not model or not vocoder or not symbols:
return redirect("/synthesis-setup")
if request.method == "GET":
return render_template("synthesis.html")
else:
text = request.form.getlist("text")
if len(text) == 1:
text = text[0]
method = request.form["text_method"]
split_text = method == "paragraph"
parent_folder = os.path.join(paths["results"],
datetime.now().strftime("%Y-%m"))
os.makedirs(parent_folder, exist_ok=True)
first_line = text[0] if type(text) == list else text
results_folder = os.path.join(
parent_folder,
get_suffix() + "-" +
re.sub("[^0-9a-zA-Z _]+", "", first_line.replace(" ", "_"))[:20])
os.makedirs(results_folder)
graph_path = os.path.join(results_folder, GRAPH_FILE)
audio_path = os.path.join(results_folder, RESULTS_FILE)
graph_web_path = os.path.relpath(graph_path).replace("\\", "/")
audio_web_path = os.path.relpath(audio_path).replace("\\", "/")
silence = float(request.form["silence"])
max_decoder_steps = int(request.form["max_decoder_steps"])
synthesize(
model,
text,
symbols,
graph_path,
audio_path,
vocoder,
silence,
max_decoder_steps=max_decoder_steps,
split_text=split_text,
)
return render_template(
"synthesis.html",
text=text,
method=method,
graph=graph_web_path,
audio=audio_web_path,
silence=silence,
max_decoder_steps=max_decoder_steps,
)
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))
