bedd1c4098
## Summary - Adds support for MP3, FLAC, OGG, and other audio formats when uploading reference voices for cloning - Replace WAV-only `audio_read()` with a `soundfile`-based implementation - Update web UI file picker to accept multiple audio formats ## Changes - `pocket_tts/data/audio.py`: Use `soundfile` library instead of Python's `wave` module - `pocket_tts/main.py`: Preserve original file extension in temp files for format detection - `pocket_tts/main.py`: Add missing `truncate=True` to CLI generate command - `pocket_tts/static/index.html`: Update file input to accept `.wav,.mp3,.flac,.ogg,.m4a,audio/*` - `pyproject.toml`: Add `soundfile>=0.12.0` dependency ## Tested - [x] Upload a WAV file as reference voice and generate speech - [x] Upload an MP3 file as reference voice and generate speech - [x] Upload a FLAC file as reference voice and generate speech - [x] Verify CLI `--voice` option works with MP3 files --------- Co-authored-by: Gabriel de Marmiesse <gabrieldemarmiesse@gmail.com> Co-authored-by: Václav Volhejn <8401624+vvolhejn@users.noreply.github.com>
74 lines
1.5 KiB
TOML
74 lines
1.5 KiB
TOML
[project]
|
|
name = "pocket-tts"
|
|
requires-python = ">= 3.10,<3.15"
|
|
description = "Kyutai's pocket-sized TTS!"
|
|
version = "1.0.1"
|
|
readme = "README.md"
|
|
dependencies = [
|
|
"numpy>=2",
|
|
# I tried 2.4.0 but the generated audio is wrong, so 2.5+ is needed.
|
|
"torch>=2.5.0",
|
|
"pydantic>=2",
|
|
"sentencepiece>=0.2.1",
|
|
"beartype>=0.22.5",
|
|
"safetensors>=0.4.0",
|
|
"typer>=0.10.0",
|
|
"typing_extensions>=4.0.0",
|
|
"fastapi>=0.100",
|
|
"uvicorn>=0.13.0",
|
|
"python-multipart>=0.0.21",
|
|
"scipy>=1.5.0",
|
|
"einops>=0.4.0",
|
|
"huggingface_hub>=0.10",
|
|
"requests>=2.20.0",
|
|
]
|
|
|
|
[project.optional-dependencies]
|
|
audio = ["soundfile>=0.12.0"]
|
|
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"coverage>=7.6.12",
|
|
"line-profiler>=5.0.0",
|
|
"pytest>=9.0.2",
|
|
"pytest-xdist>=3.8.0",
|
|
]
|
|
|
|
|
|
[tool.uv.sources]
|
|
torch = [
|
|
{ index = "pytorch-cpu" },
|
|
]
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cpu"
|
|
url = "https://download.pytorch.org/whl/cpu"
|
|
explicit = true
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
|
|
[tool.ruff.format]
|
|
line-ending = "lf"
|
|
# avoid having a trailing comma changing
|
|
# the behavior of the formatter
|
|
skip-magic-trailing-comma = true
|
|
|
|
[build-system]
|
|
requires = ["hatchling"]
|
|
build-backend = "hatchling.build"
|
|
|
|
[tool.hatch.build.targets.wheel]
|
|
packages = ["pocket_tts"]
|
|
|
|
[project.scripts]
|
|
pocket-tts = "pocket_tts.main:cli_app"
|
|
|
|
[tool.uv]
|
|
# System python distribution can have header files missing, so we use only the python
|
|
# distributions provided by uv which have everything included.
|
|
python-preference = "only-managed"
|
|
|
|
[tool.ruff.lint.flake8-tidy-imports]
|
|
ban-relative-imports = "all" |