From c0b2079fb1ef40b9ea1d67353335b0ebd7e31d5f Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 09 九月 2025 19:36:55 +0800
Subject: [PATCH] Update README.md
---
setup.py | 75 +++++++++++++++++++++++--------------
1 files changed, 47 insertions(+), 28 deletions(-)
diff --git a/setup.py b/setup.py
index dd485d3..21c51ce 100644
--- a/setup.py
+++ b/setup.py
@@ -10,44 +10,42 @@
requirements = {
"install": [
- "setuptools>=38.5.1",
- "humanfriendly",
"scipy>=1.4.1",
"librosa",
"jamo", # For kss
"PyYAML>=5.1.2",
"soundfile>=0.12.1",
- "h5py>=3.1.0",
"kaldiio>=2.17.0",
"torch_complex",
- "nltk>=3.4.5",
- # ASR
- "sentencepiece",
+ # "nltk>=3.4.5",
+ "sentencepiece", # train
"jieba",
- "rotary_embedding_torch",
- "ffmpeg",
- # TTS
- "pypinyin>=0.44.0",
- "espnet_tts_frontend",
+ # "rotary_embedding_torch",
+ # "ffmpeg-python",
+ # "pypinyin>=0.44.0",
+ # "espnet_tts_frontend",
# ENH
"pytorch_wpe",
"editdistance>=0.5.2",
- "tensorboard",
- "g2p",
- "nara_wpe",
+ # "g2p",
+ # "nara_wpe",
# PAI
"oss2",
- "edit-distance",
- "textgrid",
- "protobuf",
+ # "edit-distance",
+ # "textgrid",
+ # "protobuf",
"tqdm",
- "hdbscan",
- "umap",
+ "umap_learn",
+ "jaconv",
+ "hydra-core>=1.3.2",
+ "tensorboardX",
+ # "rotary_embedding_torch",
+ "requests",
+ "modelscope",
],
# train: The modules invoked when training only.
"train": [
"editdistance",
- "wandb",
],
# all: The modules should be optionally installled due to some reason.
# Please consider moving them to "install" occasionally
@@ -56,6 +54,7 @@
"torch_optimizer",
"fairscale",
"transformers",
+ "openai-whisper",
],
"setup": [
"numpy",
@@ -83,18 +82,28 @@
"recommonmark>=0.4.0",
"nbsphinx>=0.4.2",
"sphinx-markdown-tables>=0.0.12",
- "configargparse>=1.2.1"
+ "configargparse>=1.2.1",
+ ],
+ "llm": [
+ "transformers>=4.32.0",
+ "accelerate",
+ "tiktoken",
+ "einops",
+ "transformers_stream_generator>=0.0.4",
+ "scipy",
+ "torchvision",
+ "pillow",
+ "matplotlib",
],
}
requirements["all"].extend(requirements["train"])
+requirements["all"].extend(requirements["llm"])
requirements["test"].extend(requirements["train"])
install_requires = requirements["install"]
setup_requires = requirements["setup"]
tests_require = requirements["test"]
-extras_require = {
- k: v for k, v in requirements.items() if k not in ["install", "setup"]
-}
+extras_require = {k: v for k, v in requirements.items() if k not in ["install", "setup"]}
dirname = os.path.dirname(__file__)
version_file = os.path.join(dirname, "funasr", "version.txt")
@@ -104,7 +113,7 @@
name="funasr",
version=version,
url="https://github.com/alibaba-damo-academy/FunASR.git",
- author="Speech Lab of DAMO Academy, Alibaba Group",
+ author="Speech Lab of Alibaba Group",
author_email="funasr@list.alibaba-inc.com",
description="FunASR: A Fundamental End-to-End Speech Recognition Toolkit",
long_description=open(os.path.join(dirname, "README.md"), encoding="utf-8").read(),
@@ -129,7 +138,17 @@
"License :: OSI Approved :: Apache Software License",
"Topic :: Software Development :: Libraries :: Python Modules",
],
- entry_points={"console_scripts": [
- "funasr = funasr.bin.inference_cli:main",
- ]},
+ entry_points={
+ "console_scripts": [
+ "funasr = funasr.bin.inference:main_hydra",
+ "funasr-train = funasr.bin.train:main_hydra",
+ "funasr-export = funasr.bin.export:main_hydra",
+ "scp2jsonl = funasr.datasets.audio_datasets.scp2jsonl:main_hydra",
+ "jsonl2scp = funasr.datasets.audio_datasets.jsonl2scp:main_hydra",
+ "sensevoice2jsonl = funasr.datasets.audio_datasets.sensevoice2jsonl:main_hydra",
+ "funasr-scp2jsonl = funasr.datasets.audio_datasets.scp2jsonl:main_hydra",
+ "funasr-jsonl2scp = funasr.datasets.audio_datasets.jsonl2scp:main_hydra",
+ "funasr-sensevoice2jsonl = funasr.datasets.audio_datasets.sensevoice2jsonl:main_hydra",
+ ]
+ },
)
--
Gitblit v1.9.1