def test_hifigan_synthesis():
hifigan_model_path = os.path.join("test_samples", "hifigan.pt")
hifigan_config_path = os.path.join("test_samples", "config.json")
audio_path = "synthesized_audio.wav"
transcription_model = Silero()
hifigan = Hifigan(hifigan_model_path, hifigan_config_path)
text = "the monkeys live"
synthesize(
model=FakeModelForSynthesis(),
text=text,
graph_path=None,
audio_path=audio_path,
vocoder=hifigan,
)
assert os.path.isfile(audio_path)
assert similarity(
text, transcription_model.transcribe(audio_path)) > MIN_SYNTHESIS_SCORE
os.remove(audio_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))
"--output_folder",
help="Path to save dataset",
type=str,
default="wavs")
parser.add_argument("-s",
"--suffix",
help="String suffix for added files",
type=str,
required=True)
parser.add_argument("-l",
"--language",
help="The language to use",
type=str,
default="English")
parser.add_argument("-s",
"--symbol_path",
help="Path to symbol/alphabet file",
type=str,
default=None)
args = parser.parse_args()
extend_existing_dataset(
text_path=args.text_path,
audio_path=args.audio_path,
transcription_model=Silero(args.language),
output_folder=args.output_folder,
suffix=args.suffix,
symbols=load_symbols(args.symbol_path)
if args.symbol_path else DEFAULT_ALPHABET,
)
def test_silero():
transcription_model = Silero()
audio_path = os.path.join("test_samples", "audio.wav")
transcription = transcription_model.transcribe(audio_path)
assert similarity(TEXT, transcription) > MIN_SYNTHESIS_SCORE