minicpmo-utils 0.0.5__tar.gz → 0.0.9__tar.gz

{minicpmo_utils-0.0.5 → minicpmo_utils-0.0.9}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: minicpmo-utils
-Version: 0.0.5
+Version: 0.0.9
 Summary: Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils.
 Author: MiniCPM-o Utils Maintainers
 License: Apache-2.0
@@ -14,7 +14,11 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Requires-Dist: numpy
+Requires-Dist: MarkupSafe>=2.1.0
+Requires-Dist: Jinja2>=3.1.0
+Requires-Dist: typing-extensions>=4.12.0
+Requires-Dist: packaging>=23.0
+Requires-Dist: numpy>=1.24.0
 Requires-Dist: pillow==10.4.0
 Requires-Dist: librosa==0.9.0
 Requires-Dist: decord==0.6.0
@@ -24,11 +28,12 @@ Provides-Extra: tts
 Requires-Dist: torch>=2.3.0; extra == "tts"
 Requires-Dist: torchaudio>=2.3.0; extra == "tts"
 Requires-Dist: transformers<4.53.0,>=4.51.0; extra == "tts"
+Requires-Dist: safetensors>=0.4.3; extra == "tts"
 Requires-Dist: onnxruntime<=1.21.0,>=1.18.0; extra == "tts"
 Requires-Dist: onnx; extra == "tts"
 Requires-Dist: hyperpyyaml; extra == "tts"
-Requires-Dist: openai-whisper==20231117; extra == "tts"
-Requires-Dist: tqdm; extra == "tts"
+Requires-Dist: openai-whisper; extra == "tts"
+Requires-Dist: tqdm>=4.66.0; extra == "tts"
 Requires-Dist: tiktoken; extra == "tts"
 Requires-Dist: inflect; extra == "tts"
 Requires-Dist: omegaconf>=2.0.6; extra == "tts"
@@ -42,24 +47,15 @@ Requires-Dist: matplotlib; extra == "tts"
 Requires-Dist: wget; extra == "tts"
 Requires-Dist: pyarrow; extra == "tts"
 Requires-Dist: pyworld; extra == "tts"
-Requires-Dist: scipy; extra == "tts"
+Requires-Dist: scipy>=1.10.0; extra == "tts"
 Requires-Dist: pyyaml; extra == "tts"
 Requires-Dist: regex; extra == "tts"
 Requires-Dist: soundfile==0.12.1; extra == "tts"
 Requires-Dist: diffusers==0.29.0; extra == "tts"
 Provides-Extra: streaming
 Requires-Dist: minicpmo-utils[tts]; extra == "streaming"
-Provides-Extra: streaming-flash
-Requires-Dist: minicpmo-utils[streaming]; extra == "streaming-flash"
-Requires-Dist: flash-attn>=2.6.0; sys_platform == "linux" and extra == "streaming-flash"
-Requires-Dist: triton>=2.3.0; sys_platform == "linux" and extra == "streaming-flash"
-Requires-Dist: safetensors; extra == "streaming-flash"
-Requires-Dist: pynvml; extra == "streaming-flash"
-Requires-Dist: xxhash; extra == "streaming-flash"
-Provides-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"
+Requires-Dist: minicpmo-utils[streaming,tts]; extra == "all"
 
 ## minicpmo-utils
 

{minicpmo_utils-0.0.5 → minicpmo_utils-0.0.9}/pyproject.toml

@@ -1,10 +1,10 @@
 [build-system]
-requires = ["setuptools>=69", "wheel"]
+requires = ["setuptools>=65", "wheel"]
 build-backend = "setuptools.build_meta"
 
 [project]
 name = "minicpmo-utils"
-version = "0.0.5"
+version = "0.0.9"
 description = "Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils."
 readme = "README.md"
 requires-python = ">=3.10"
@@ -31,7 +31,12 @@ classifiers = [
 #   - s3tokenizer (来自 S3Tokenizer-main)
 #   - minicpmo (本项目扩展 utils 的统一入口：from minicpmo.utils import ...)
 dependencies = [
-  "numpy",
+  # 锁定下限，避免 pip 回退到旧版本，加速依赖解析
+  "MarkupSafe>=2.1.0",
+  "Jinja2>=3.1.0",
+  "typing-extensions>=4.12.0",
+  "packaging>=23.0",
+  "numpy>=1.24.0",
   "pillow==10.4.0",
   "librosa==0.9.0",
   "decord==0.6.0",
@@ -45,11 +50,12 @@ tts = [
   "torch>=2.3.0",
   "torchaudio>=2.3.0",
   "transformers>=4.51.0,<4.53.0",  # 4.52+ 有兼容性问题
+  "safetensors>=0.4.3",
   "onnxruntime>=1.18.0,<=1.21.0",
   "onnx",
   "hyperpyyaml",
-  "openai-whisper==20231117",
-  "tqdm",
+  "openai-whisper",
+  "tqdm>=4.66.0",
   "tiktoken",
   "inflect",
   "omegaconf>=2.0.6",
@@ -64,7 +70,7 @@ tts = [
   "pyarrow",
   "pyworld",
   # 新增依赖
-  "scipy",
+  "scipy>=1.10.0",
   "pyyaml",
   "regex",
   "soundfile==0.12.1",
@@ -76,23 +82,23 @@ streaming = [
   "minicpmo-utils[tts]",  # streaming 依赖 tts
 ]
 
-# stepaudio2 Flash 推理引擎依赖（flashcosyvoice.engine 模块需要）
-streaming-flash = [
-  "minicpmo-utils[streaming]",
-  "flash-attn>=2.6.0; sys_platform == 'linux'",
-  "triton>=2.3.0; sys_platform == 'linux'",
-  "safetensors",
-  "pynvml",
-  "xxhash",
-]
+# # stepaudio2 Flash 推理引擎依赖（flashcosyvoice.engine 模块需要）
+# streaming-flash = [
+#   "minicpmo-utils[streaming]",
+#   "flash-attn>=2.6.0; sys_platform == 'linux'",
+#   "triton>=2.3.0; sys_platform == 'linux'",
+#   "safetensors>=0.4.3",
+#   "pynvml",
+#   "xxhash",
+# ]
 
-# 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,<=1.23.2; sys_platform == 'linux'",
-]
+# # 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,<=1.23.2; sys_platform == 'linux'",
+# ]
 
 all = [
-  "minicpmo-utils[tts,streaming,gpu]",
+  "minicpmo-utils[tts,streaming]",
 ]
 
 [tool.setuptools]

{minicpmo_utils-0.0.5 → minicpmo_utils-0.0.9}/src/minicpmo/utils.py

@@ -26,84 +26,6 @@ MAX_NUM_FRAMES = int(os.getenv("MAX_NUM_FRAMES", 64))
 VIDEO_MME_DURATION = os.getenv("VIDEO_MME_DURATION", "ALL")
 
 
-def find_cjk_font():
-    """
-    查找支持中文的字体。
-    按优先级返回字体名称或路径，如果找不到则返回 None。
-    """
-    # 常见的中文字体名称（按优先级排列）
-    font_names = [
-        # Noto CJK 字体（推荐）
-        "Noto Sans CJK SC",
-        "Noto Sans CJK",
-        "NotoSansCJK-Regular",
-        # 文泉驿字体
-        "WenQuanYi Zen Hei",
-        "WenQuanYi Micro Hei",
-        "文泉驿正黑",
-        "文泉驿微米黑",
-        # 思源字体
-        "Source Han Sans SC",
-        "Source Han Sans CN",
-        # 其他常见中文字体
-        "SimHei",
-        "Microsoft YaHei",
-        "PingFang SC",
-        "Hiragino Sans GB",
-        "STHeiti",
-        "AR PL UMing CN",
-        "AR PL UKai CN",
-    ]
-
-    # 常见的中文字体文件路径
-    font_paths = [
-        # Noto CJK
-        "/usr/share/fonts/opentype/noto/NotoSansCJK-Regular.ttc",
-        "/usr/share/fonts/noto-cjk/NotoSansCJK-Regular.ttc",
-        "/usr/share/fonts/google-noto-cjk/NotoSansCJK-Regular.ttc",
-        "/usr/share/fonts/truetype/noto/NotoSansCJK-Regular.ttc",
-        # 文泉驿
-        "/usr/share/fonts/truetype/wqy/wqy-zenhei.ttc",
-        "/usr/share/fonts/truetype/wqy/wqy-microhei.ttc",
-        "/usr/share/fonts/wenquanyi/wqy-zenhei/wqy-zenhei.ttc",
-        "/usr/share/fonts/wenquanyi/wqy-microhei/wqy-microhei.ttc",
-        # macOS
-        "/System/Library/Fonts/PingFang.ttc",
-        "/Library/Fonts/Arial Unicode.ttf",
-        # Windows (WSL)
-        "/mnt/c/Windows/Fonts/msyh.ttc",
-        "/mnt/c/Windows/Fonts/simhei.ttf",
-    ]
-
-    # 首先尝试使用 fc-list 查找已安装的中文字体
-    try:
-        result = subprocess.run(
-            ["fc-list", ":lang=zh", "-f", "%{family}\n"],
-            capture_output=True,
-            text=True,
-            timeout=5,
-        )
-        if result.returncode == 0:
-            installed_fonts = set(result.stdout.strip().split("\n"))
-            for font_name in font_names:
-                for installed in installed_fonts:
-                    if font_name.lower() in installed.lower():
-                        logger.info(f"Found CJK font via fc-list: {installed}")
-                        return installed.split(",")[0]  # 取第一个名称
-    except Exception as e:
-        logger.debug(f"fc-list failed: {e}")
-
-    # 然后检查常见的字体文件路径
-    for path in font_paths:
-        if os.path.exists(path):
-            logger.info(f"Found CJK font file: {path}")
-            return path
-
-    logger.warning("No CJK font found. Chinese subtitles may display as boxes/garbled text.")
-    logger.warning("Install Chinese fonts with: sudo apt-get install fonts-noto-cjk")
-    return None
-
-
 def concat_images(images, bg_color=(255, 255, 255), cell_size=None, line_color=(0, 0, 0), line_width=6):
     """
     images: List[PIL.Image.Image]
@@ -649,18 +571,9 @@ def generate_duplex_video(
 
     if has_subtitles:
         srt_path_escaped = srt_path.replace("\\", "\\\\").replace("'", "'\\''").replace(":", "\\:")
-
-        # 查找支持中文的字体
-        cjk_font = find_cjk_font()
-        font_style = ""
-        if cjk_font:
-            # 转义字体路径/名称中的特殊字符
-            font_escaped = cjk_font.replace("\\", "\\\\").replace("'", "'\\''").replace(":", "\\:")
-            font_style = f"FontName={font_escaped},"
-
         subtitle_filter = (
             f"subtitles='{srt_path_escaped}':"
-            f"force_style='{font_style}FontSize=28,"
+            f"force_style='FontSize=28,"
             f"PrimaryColour=&H00FFFFFF,"
             f"OutlineColour=&H00000000,"
             f"BorderStyle=3,"

{minicpmo_utils-0.0.5 → minicpmo_utils-0.0.9}/src/minicpmo_utils.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: minicpmo-utils
-Version: 0.0.5
+Version: 0.0.9
 Summary: Unified utilities package for MiniCPM-o: includes cosyvoice + stepaudio2 and extensible utils.
 Author: MiniCPM-o Utils Maintainers
 License: Apache-2.0
@@ -14,7 +14,11 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
-Requires-Dist: numpy
+Requires-Dist: MarkupSafe>=2.1.0
+Requires-Dist: Jinja2>=3.1.0
+Requires-Dist: typing-extensions>=4.12.0
+Requires-Dist: packaging>=23.0
+Requires-Dist: numpy>=1.24.0
 Requires-Dist: pillow==10.4.0
 Requires-Dist: librosa==0.9.0
 Requires-Dist: decord==0.6.0
@@ -24,11 +28,12 @@ Provides-Extra: tts
 Requires-Dist: torch>=2.3.0; extra == "tts"
 Requires-Dist: torchaudio>=2.3.0; extra == "tts"
 Requires-Dist: transformers<4.53.0,>=4.51.0; extra == "tts"
+Requires-Dist: safetensors>=0.4.3; extra == "tts"
 Requires-Dist: onnxruntime<=1.21.0,>=1.18.0; extra == "tts"
 Requires-Dist: onnx; extra == "tts"
 Requires-Dist: hyperpyyaml; extra == "tts"
-Requires-Dist: openai-whisper==20231117; extra == "tts"
-Requires-Dist: tqdm; extra == "tts"
+Requires-Dist: openai-whisper; extra == "tts"
+Requires-Dist: tqdm>=4.66.0; extra == "tts"
 Requires-Dist: tiktoken; extra == "tts"
 Requires-Dist: inflect; extra == "tts"
 Requires-Dist: omegaconf>=2.0.6; extra == "tts"
@@ -42,24 +47,15 @@ Requires-Dist: matplotlib; extra == "tts"
 Requires-Dist: wget; extra == "tts"
 Requires-Dist: pyarrow; extra == "tts"
 Requires-Dist: pyworld; extra == "tts"
-Requires-Dist: scipy; extra == "tts"
+Requires-Dist: scipy>=1.10.0; extra == "tts"
 Requires-Dist: pyyaml; extra == "tts"
 Requires-Dist: regex; extra == "tts"
 Requires-Dist: soundfile==0.12.1; extra == "tts"
 Requires-Dist: diffusers==0.29.0; extra == "tts"
 Provides-Extra: streaming
 Requires-Dist: minicpmo-utils[tts]; extra == "streaming"
-Provides-Extra: streaming-flash
-Requires-Dist: minicpmo-utils[streaming]; extra == "streaming-flash"
-Requires-Dist: flash-attn>=2.6.0; sys_platform == "linux" and extra == "streaming-flash"
-Requires-Dist: triton>=2.3.0; sys_platform == "linux" and extra == "streaming-flash"
-Requires-Dist: safetensors; extra == "streaming-flash"
-Requires-Dist: pynvml; extra == "streaming-flash"
-Requires-Dist: xxhash; extra == "streaming-flash"
-Provides-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"
+Requires-Dist: minicpmo-utils[streaming,tts]; extra == "all"
 
 ## minicpmo-utils
 

{minicpmo_utils-0.0.5 → minicpmo_utils-0.0.9}/src/minicpmo_utils.egg-info/requires.txt

@@ -1,4 +1,8 @@
-numpy
+MarkupSafe>=2.1.0
+Jinja2>=3.1.0
+typing-extensions>=4.12.0
+packaging>=23.0
+numpy>=1.24.0
 pillow==10.4.0
 librosa==0.9.0
 decord==0.6.0
@@ -6,35 +10,21 @@ moviepy==2.1.2
 numba==0.61.2
 
 [all]
-minicpmo-utils[gpu,streaming,tts]
-
-[gpu]
-
-[gpu:sys_platform == "linux"]
-onnxruntime-gpu<=1.23.2,>=1.18.0
+minicpmo-utils[streaming,tts]
 
 [streaming]
 minicpmo-utils[tts]
 
-[streaming-flash]
-minicpmo-utils[streaming]
-safetensors
-pynvml
-xxhash
-
-[streaming-flash:sys_platform == "linux"]
-flash-attn>=2.6.0
-triton>=2.3.0
-
 [tts]
 torch>=2.3.0
 torchaudio>=2.3.0
 transformers<4.53.0,>=4.51.0
+safetensors>=0.4.3
 onnxruntime<=1.21.0,>=1.18.0
 onnx
 hyperpyyaml
-openai-whisper==20231117
-tqdm
+openai-whisper
+tqdm>=4.66.0
 tiktoken
 inflect
 omegaconf>=2.0.6
@@ -48,7 +38,7 @@ matplotlib
 wget
 pyarrow
 pyworld
-scipy
+scipy>=1.10.0
 pyyaml
 regex
 soundfile==0.12.1