minicpmo-utils 0.1.0__tar.gz → 0.1.2__tar.gz

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: minicpmo-utils
-Version: 0.1.0
+Version: 0.1.2
 Summary: Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils.
 Author: MiniCPM-o Utils Maintainers
 License: Apache-2.0
@@ -14,23 +14,31 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Requires-Dist: torch>=2.3.0
-Requires-Dist: torchaudio>=2.3.0
-Requires-Dist: transformers>=4.49.0
 Requires-Dist: numpy
-Requires-Dist: hyperpyyaml
-Requires-Dist: modelscope
-Requires-Dist: openai-whisper
-Requires-Dist: tqdm
-Requires-Dist: tiktoken
-Requires-Dist: inflect
-Requires-Dist: omegaconf
-Requires-Dist: einops
-Requires-Dist: librosa
-Requires-Dist: onnxruntime>=1.18.0
-Requires-Dist: diffusers
+Requires-Dist: pillow==10.4.0
+Requires-Dist: librosa==0.9.0
+Requires-Dist: decord==0.6.0
+Requires-Dist: moviepy==2.1.2
+Provides-Extra: tts
+Requires-Dist: torch>=2.3.0; extra == "tts"
+Requires-Dist: torchaudio>=2.3.0; extra == "tts"
+Requires-Dist: transformers>=4.49.0; extra == "tts"
+Requires-Dist: hyperpyyaml; extra == "tts"
+Requires-Dist: openai-whisper; extra == "tts"
+Requires-Dist: tqdm; extra == "tts"
+Requires-Dist: tiktoken; extra == "tts"
+Requires-Dist: inflect; extra == "tts"
+Requires-Dist: omegaconf; extra == "tts"
+Requires-Dist: einops; extra == "tts"
+Provides-Extra: streaming
+Requires-Dist: minicpmo-utils[tts]; extra == "streaming"
+Requires-Dist: onnxruntime<=1.21.0,>=1.18.0; extra == "streaming"
+Requires-Dist: onnx; extra == "streaming"
+Requires-Dist: diffusers; extra == "streaming"
 Provides-Extra: gpu
-Requires-Dist: onnxruntime-gpu>=1.18.0; sys_platform == "linux" and extra == "gpu"
+Requires-Dist: onnxruntime-gpu<=1.23.2,>=1.18.0; sys_platform == "linux" and extra == "gpu"
+Provides-Extra: all
+Requires-Dist: minicpmo-utils[gpu,streaming,tts]; extra == "all"
 
 ## minicpmo-utils
 
@@ -38,17 +46,32 @@ Requires-Dist: onnxruntime-gpu>=1.18.0; sys_platform == "linux" and extra == "gp
 
 ### 安装方式
 
-- 从源码本地安装（开发态，可编辑）：
+- 从源码本地安装（开发态，可编辑，默认只装公共依赖）：
 ```bash
 cd minicpmo-utils
 pip install -e .
 ```
 
+- 如果只想安装 cosyvoice 相关依赖（TTS）：
+```bash
+pip install -e .[tts]
+```
+
+- 如果只想安装 stepaudio2 / streaming 相关依赖：
+```bash
+pip install -e .[streaming]
+```
+
+- 同时安装 cosyvoice + stepaudio2 相关依赖：
+```bash
+pip install -e .[tts,streaming]
+```
+
 - 构建并安装 wheel（推荐分发）：
 ```bash
 cd minicpmo-utils
 python -m build        # 生成 dist/*.whl
-pip install dist/minicpmo_utils-0.1.0-py3-none-any.whl
+pip install \"dist/minicpmo_utils-0.1.0-py3-none-any.whl[tts,streaming]\"
 ```
 
 ### 导入方式

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/README.md

@@ -4,17 +4,32 @@
 
 ### 安装方式
 
-- 从源码本地安装（开发态，可编辑）：
+- 从源码本地安装（开发态，可编辑，默认只装公共依赖）：
 ```bash
 cd minicpmo-utils
 pip install -e .
 ```
 
+- 如果只想安装 cosyvoice 相关依赖（TTS）：
+```bash
+pip install -e .[tts]
+```
+
+- 如果只想安装 stepaudio2 / streaming 相关依赖：
+```bash
+pip install -e .[streaming]
+```
+
+- 同时安装 cosyvoice + stepaudio2 相关依赖：
+```bash
+pip install -e .[tts,streaming]
+```
+
 - 构建并安装 wheel（推荐分发）：
 ```bash
 cd minicpmo-utils
 python -m build        # 生成 dist/*.whl
-pip install dist/minicpmo_utils-0.1.0-py3-none-any.whl
+pip install \"dist/minicpmo_utils-0.1.0-py3-none-any.whl[tts,streaming]\"
 ```
 
 ### 导入方式

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "minicpmo-utils"
-version = "0.1.0"
+version = "0.1.2"
 description = "Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -31,34 +31,43 @@ classifiers = [
 #   - s3tokenizer (来自 S3Tokenizer-main)
 #   - minicpmo (本项目扩展 utils 的统一入口：from minicpmo.utils import ...)
 dependencies = [
-  # Core ML frameworks (align to stepaudio2's requirements)
+  "numpy",
+  "pillow==10.4.0",
+  "librosa==0.9.0",
+  "decord==0.6.0",
+  "moviepy==2.1.2"
+]
+
+[project.optional-dependencies]
+# cosyvoice TTS 相关依赖
+tts = [
   "torch>=2.3.0",
   "torchaudio>=2.3.0",
   "transformers>=4.49.0",
-
-  # Shared / common
-  "numpy",
   "hyperpyyaml",
-
-  # cosyvoice side
-  "modelscope",
   "openai-whisper",
   "tqdm",
   "tiktoken",
   "inflect",
   "omegaconf",
   "einops",
+]
 
-  # stepaudio2 side
-  "librosa",
-  "onnxruntime>=1.18.0",
+# stepaudio2 / streaming 相关依赖
+streaming = [
+  "minicpmo-utils[tts]",  # streaming 依赖 tts
+  "onnxruntime>=1.18.0,<=1.21.0",
+  "onnx",
   "diffusers",
 ]
 
-[project.optional-dependencies]
-# Linux GPU onnxruntime can be heavy and environment-specific; keep as an opt-in extra.
+# Linux GPU onnxruntime 可以很重，且与环境强相关，保留为可选 extra
 gpu = [
-  "onnxruntime-gpu>=1.18.0; sys_platform == 'linux'",
+  "onnxruntime-gpu>=1.18.0,<=1.23.2; sys_platform == 'linux'",
+]
+
+all = [
+  "minicpmo-utils[tts,streaming,gpu]",
 ]
 
 [tool.setuptools]

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/src/cosyvoice/cli/cosyvoice.py

@@ -16,7 +16,6 @@ import time
 from typing import Generator
 from tqdm import tqdm
 from hyperpyyaml import load_hyperpyyaml
-from modelscope import snapshot_download
 import torch
 from cosyvoice.cli.frontend import CosyVoiceFrontEnd
 from cosyvoice.cli.model import CosyVoiceModel, CosyVoice2Model
@@ -30,8 +29,6 @@ class CosyVoice:
         self.instruct = True if '-Instruct' in model_dir else False
         self.model_dir = model_dir
         self.fp16 = fp16
-        if not os.path.exists(model_dir):
-            model_dir = snapshot_download(model_dir)
         hyper_yaml_path = '{}/cosyvoice.yaml'.format(model_dir)
         if not os.path.exists(hyper_yaml_path):
             raise ValueError('{} not found!'.format(hyper_yaml_path))
@@ -154,8 +151,6 @@ class CosyVoice2(CosyVoice):
         self.instruct = True if '-Instruct' in model_dir else False
         self.model_dir = model_dir
         self.fp16 = fp16
-        if not os.path.exists(model_dir):
-            model_dir = snapshot_download(model_dir)
         
         if config_path is None:
             config_path = f'{model_dir}/cosyvoice2.yaml'

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/src/minicpmo_utils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: minicpmo-utils
-Version: 0.1.0
+Version: 0.1.2
 Summary: Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils.
 Author: MiniCPM-o Utils Maintainers
 License: Apache-2.0
@@ -14,23 +14,31 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Requires-Dist: torch>=2.3.0
-Requires-Dist: torchaudio>=2.3.0
-Requires-Dist: transformers>=4.49.0
 Requires-Dist: numpy
-Requires-Dist: hyperpyyaml
-Requires-Dist: modelscope
-Requires-Dist: openai-whisper
-Requires-Dist: tqdm
-Requires-Dist: tiktoken
-Requires-Dist: inflect
-Requires-Dist: omegaconf
-Requires-Dist: einops
-Requires-Dist: librosa
-Requires-Dist: onnxruntime>=1.18.0
-Requires-Dist: diffusers
+Requires-Dist: pillow==10.4.0
+Requires-Dist: librosa==0.9.0
+Requires-Dist: decord==0.6.0
+Requires-Dist: moviepy==2.1.2
+Provides-Extra: tts
+Requires-Dist: torch>=2.3.0; extra == "tts"
+Requires-Dist: torchaudio>=2.3.0; extra == "tts"
+Requires-Dist: transformers>=4.49.0; extra == "tts"
+Requires-Dist: hyperpyyaml; extra == "tts"
+Requires-Dist: openai-whisper; extra == "tts"
+Requires-Dist: tqdm; extra == "tts"
+Requires-Dist: tiktoken; extra == "tts"
+Requires-Dist: inflect; extra == "tts"
+Requires-Dist: omegaconf; extra == "tts"
+Requires-Dist: einops; extra == "tts"
+Provides-Extra: streaming
+Requires-Dist: minicpmo-utils[tts]; extra == "streaming"
+Requires-Dist: onnxruntime<=1.21.0,>=1.18.0; extra == "streaming"
+Requires-Dist: onnx; extra == "streaming"
+Requires-Dist: diffusers; extra == "streaming"
 Provides-Extra: gpu
-Requires-Dist: onnxruntime-gpu>=1.18.0; sys_platform == "linux" and extra == "gpu"
+Requires-Dist: onnxruntime-gpu<=1.23.2,>=1.18.0; sys_platform == "linux" and extra == "gpu"
+Provides-Extra: all
+Requires-Dist: minicpmo-utils[gpu,streaming,tts]; extra == "all"
 
 ## minicpmo-utils
 
@@ -38,17 +46,32 @@ Requires-Dist: onnxruntime-gpu>=1.18.0; sys_platform == "linux" and extra == "gp
 
 ### 安装方式
 
-- 从源码本地安装（开发态，可编辑）：
+- 从源码本地安装（开发态，可编辑，默认只装公共依赖）：
 ```bash
 cd minicpmo-utils
 pip install -e .
 ```
 
+- 如果只想安装 cosyvoice 相关依赖（TTS）：
+```bash
+pip install -e .[tts]
+```
+
+- 如果只想安装 stepaudio2 / streaming 相关依赖：
+```bash
+pip install -e .[streaming]
+```
+
+- 同时安装 cosyvoice + stepaudio2 相关依赖：
+```bash
+pip install -e .[tts,streaming]
+```
+
 - 构建并安装 wheel（推荐分发）：
 ```bash
 cd minicpmo-utils
 python -m build        # 生成 dist/*.whl
-pip install dist/minicpmo_utils-0.1.0-py3-none-any.whl
+pip install \"dist/minicpmo_utils-0.1.0-py3-none-any.whl[tts,streaming]\"
 ```
 
 ### 导入方式

minicpmo_utils-0.1.2/src/minicpmo_utils.egg-info/requires.txt

@@ -0,0 +1,31 @@
+numpy
+pillow==10.4.0
+librosa==0.9.0
+decord==0.6.0
+moviepy==2.1.2
+
+[all]
+minicpmo-utils[gpu,streaming,tts]
+
+[gpu]
+
+[gpu:sys_platform == "linux"]
+onnxruntime-gpu<=1.23.2,>=1.18.0
+
+[streaming]
+minicpmo-utils[tts]
+onnxruntime<=1.21.0,>=1.18.0
+onnx
+diffusers
+
+[tts]
+torch>=2.3.0
+torchaudio>=2.3.0
+transformers>=4.49.0
+hyperpyyaml
+openai-whisper
+tqdm
+tiktoken
+inflect
+omegaconf
+einops

{minicpmo_utils-0.1.0 → minicpmo_utils-0.1.2}/src/stepaudio2/token2wav.py

@@ -7,7 +7,6 @@ import torchaudio
 import s3tokenizer
 import onnxruntime
 import numpy as np
-from copy import deepcopy
 
 import torchaudio.compliance.kaldi as kaldi
 from stepaudio2.flashcosyvoice.modules.hifigan import HiFTGenerator

minicpmo_utils-0.1.0/src/minicpmo_utils.egg-info/requires.txt

@@ -1,20 +0,0 @@
-torch>=2.3.0
-torchaudio>=2.3.0
-transformers>=4.49.0
-numpy
-hyperpyyaml
-modelscope
-openai-whisper
-tqdm
-tiktoken
-inflect
-omegaconf
-einops
-librosa
-onnxruntime>=1.18.0
-diffusers
-
-[gpu]
-
-[gpu:sys_platform == "linux"]
-onnxruntime-gpu>=1.18.0