diff --git a/poetry.lock b/poetry.lock index 77b0549..9a1b6d7 100644 --- a/poetry.lock +++ b/poetry.lock @@ -230,18 +230,6 @@ files = [ [package.extras] dev = ["backports.zoneinfo ; python_version < \"3.9\"", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata ; sys_platform == \"win32\""] -[[package]] -name = "blinker" -version = "1.9.0" -description = "Fast, simple object-to-object and broadcast signaling" -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "blinker-1.9.0-py3-none-any.whl", hash = "sha256:ba0efaa9080b619ff2f3459d1d500c57bddea4a6b424b60a91141db6fd2f08bc"}, - {file = "blinker-1.9.0.tar.gz", hash = "sha256:b4ce2265a7abece45e7cc896e98dbebe6cead56bcf805a3d23136d145f5445bf"}, -] - [[package]] name = "blis" version = "0.7.11" @@ -752,7 +740,6 @@ coqui-tts-trainer = ">=0.2.0,<0.3.0" cython = ">=3.0.0" einops = ">=0.6.0" encodec = ">=0.1.1" -flask = {version = ">=3.0.0", optional = true, markers = "extra == \"server\""} fsspec = {version = ">=2023.6.0", extras = ["http"]} gruut = {version = ">=2.4.0", extras = ["de", "es", "fr"]} inflect = ">=5.6.0" @@ -803,7 +790,6 @@ coqui-tts-trainer = ">=0.2.0,<0.3.0" cython = ">=3.0.0" einops = ">=0.6.0" encodec = ">=0.1.1" -flask = {version = ">=3.0.0", optional = true, markers = "extra == \"server\""} fsspec = {version = ">=2023.6.0", extras = ["http"]} gruut = {version = ">=2.4.0", extras = ["de", "es", "fr"]} inflect = ">=5.6.0" @@ -1111,30 +1097,6 @@ docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3) testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"] typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""] -[[package]] -name = "flask" -version = "3.1.0" -description = "A simple framework for building complex web applications." -optional = false -python-versions = ">=3.9" -groups = ["main"] -files = [ - {file = "flask-3.1.0-py3-none-any.whl", hash = "sha256:d667207822eb83f1c4b50949b1623c8fc8d51f2341d65f72e1a1815397551136"}, - {file = "flask-3.1.0.tar.gz", hash = "sha256:5f873c5184c897c8d9d1b05df1e3d01b14910ce69607a117bd3277098a5836ac"}, -] - -[package.dependencies] -blinker = ">=1.9" -click = ">=8.1.3" -importlib-metadata = {version = ">=3.6", markers = "python_version < \"3.10\""} -itsdangerous = ">=2.2" -Jinja2 = ">=3.1.2" -Werkzeug = ">=3.1" - -[package.extras] -async = ["asgiref (>=3.2)"] -dotenv = ["python-dotenv"] - [[package]] name = "fonttools" version = "4.56.0" @@ -1641,18 +1603,6 @@ enabler = ["pytest-enabler (>=2.2)"] test = ["pygments", "pytest (>=6,!=8.1.*)"] type = ["pytest-mypy"] -[[package]] -name = "itsdangerous" -version = "2.2.0" -description = "Safely pass data to untrusted environments and back." -optional = false -python-versions = ">=3.8" -groups = ["main"] -files = [ - {file = "itsdangerous-2.2.0-py3-none-any.whl", hash = "sha256:c6242fc49e35958c8b15141343aa660db5fc54d4f13a1db01a3f5891b98700ef"}, - {file = "itsdangerous-2.2.0.tar.gz", hash = "sha256:e0050c0b7da1eea53ffaf149c0cfbb5c6e2e2b69c4bef22c81fa6eb73e5f6173"}, -] - [[package]] name = "jinja2" version = "3.1.6" @@ -5351,4 +5301,4 @@ type = ["pytest-mypy"] [metadata] lock-version = "2.1" python-versions = ">=3.9.0, <3.12" -content-hash = "d481879db7e84cbcfef78e7f6e832087f051ed74dde2263cba1c86e958194bc0" +content-hash = "ee701530da0d8840e30fe07acbf372b4aec14e688bebf20ec5bd5eaa96270073" diff --git a/hello_world.py b/test_xtts.py similarity index 85% rename from hello_world.py rename to test_xtts.py index cff6efd..e49b6a3 100644 --- a/hello_world.py +++ b/test_xtts.py @@ -4,6 +4,7 @@ from TTS.api import TTS # Get device if torch.cuda.is_available(): + print('Running on gpu') device = "cuda" else: print('Running on cpu') @@ -46,16 +47,19 @@ for idx, speaker in enumerate(tts.speakers, 1): safe_name = speaker.replace(" ", "_").replace("/", "-") filename = f"output_wav/{safe_name}.wav" - # Generate audio + # Generate audio with timing + step_start = time.time() tts.tts_to_file( text="Bitte beachten Sie: Sicherheitscheck 5 ist jetzt geƶffnet. Bitte warten Sie im bereitgestellten Wartebereich, bis Sie aufgerufen werden.", speaker=speaker, language="de", file_path=filename ) + step_end = time.time() - # Print progress - progress = f"[{idx}/{total_speakers}] {filename}" + # Print progress with duration + step_duration = step_end - step_start + progress = f"[{idx}/{total_speakers}] {filename} - {step_duration:.2f}s" print(progress) end_gen = time.time() print(f"Generation time: {end_gen - start_gen:.2f} seconds")