[pull] main from m-bain:main

.python-version

@@ -0,0 +1 @@
+3.10

README.md

@@ -62,6 +62,15 @@ This repository provides fast automatic speech recognition (70x realtime with la
 
 <h2 align="left" id="setup">Setup ⚙️</h2>
 
+### 0. CUDA Installation
+
+To use WhisperX with GPU acceleration, install the CUDA toolkit 12.8 before WhisperX. Skip this step if using only the CPU.
+
+- For **Linux** users, install the CUDA toolkit 12.8 following this guide:
+  [CUDA Installation Guide for Linux](https://docs.nvidia.com/cuda/cuda-installation-guide-linux/).
+- For **Windows** users, download and install the CUDA toolkit 12.8:
+  [CUDA Downloads](https://developer.nvidia.com/cuda-12-8-1-download-archive).
+
 ### 1. Simple Installation (Recommended)
 
 The easiest way to install WhisperX is through PyPi:
@@ -102,25 +111,6 @@ uv sync --all-extras --dev
 
 You may also need to install ffmpeg, rust etc. Follow openAI instructions here https://github.com/openai/whisper#setup.
 
-### Common Issues & Troubleshooting 🔧
-
-#### libcudnn Dependencies (GPU Users)
-
-If you're using WhisperX with GPU support and encounter errors like:
-
-- `Could not load library libcudnn_ops_infer.so.8`
-- `Unable to load any of {libcudnn_cnn.so.9.1.0, libcudnn_cnn.so.9.1, libcudnn_cnn.so.9, libcudnn_cnn.so}`
-- `libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory`
-
-This means your system is missing the CUDA Deep Neural Network library (cuDNN). This library is needed for GPU acceleration but isn't always installed by default.
-
-**Install cuDNN (example for apt based systems):**
-
-```bash
-sudo apt update
-sudo apt install libcudnn8 libcudnn8-dev -y
-```
-
 ### Speaker Diarization
 
 To **enable Speaker Diarization**, include your Hugging Face access token (read) that you can generate from [Here](https://huggingface.co/settings/tokens) after the `--hf_token` argument and accept the user agreement for the following models: [Segmentation](https://huggingface.co/pyannote/segmentation-3.0) and [Speaker-Diarization-3.1](https://huggingface.co/pyannote/speaker-diarization-3.1) (if you choose to use Speaker-Diarization 2.x, follow requirements [here](https://huggingface.co/pyannote/speaker-diarization) instead.)

pyproject.toml

@@ -2,23 +2,26 @@
 urls = { repository = "https://github.com/m-bain/whisperx" }
 authors = [{ name = "Max Bain" }]
 name = "whisperx"
-version = "3.4.3"
+version = "3.5.0"
 description = "Time-Accurate Automatic Speech Recognition using Whisper."
 readme = "README.md"
 requires-python = ">=3.9, <3.13"
 license = { text = "BSD-2-Clause" }
 
 dependencies = [
-    "ctranslate2<4.5.0",
+    "ctranslate2>=4.5.0",
     "faster-whisper>=1.1.1",
     "nltk>=3.9.1",
-    "numpy>=2.0.2",
-    "onnxruntime>=1.19",
-    "pandas>=2.2.3",
+    # Restrict numpy, onnxruntime, pandas, av to be compatible with Python 3.9
+    "numpy>=2.0.2,<2.1.0",
+    "onnxruntime>=1.19,<1.20.0",
+    "pandas>=2.2.3,<2.3.0",
+    "av<16.0.0",
     "pyannote-audio>=3.3.2,<4.0.0",
-    "torch>=2.5.1",
-    "torchaudio>=2.5.1",
+    "torch>=2.7.1",
+    "torchaudio",
     "transformers>=4.48.0",
+    "triton>=3.3.0; sys_platform == 'linux'" # only install triton on Linux
 ]
 
 
@@ -34,3 +37,28 @@ include-package-data = true
 [tool.setuptools.packages.find]
 where = ["."]
 include = ["whisperx*"]
+
+[tool.uv.sources]
+torch = [
+  { index = "pytorch-cpu", marker = "sys_platform == 'darwin'" },
+  { index = "pytorch-cpu", marker = "platform_machine != 'x86_64' and sys_platform != 'darwin'" },
+  { index = "pytorch", marker = "platform_machine == 'x86_64' and sys_platform != 'darwin'" },
+]
+torchaudio = [
+  { index = "pytorch-cpu", marker = "sys_platform == 'darwin'" },
+  { index = "pytorch-cpu", marker = "platform_machine != 'x86_64' and sys_platform != 'darwin'" },
+  { index = "pytorch", marker = "platform_machine == 'x86_64' and sys_platform != 'darwin'" },
+]
+triton = [
+  { index = "pytorch", marker = "sys_platform == 'linux'" },
+]
+
+[[tool.uv.index]]
+name = "pytorch"
+url = "https://download.pytorch.org/whl/cu128"
+explicit = true
+
+[[tool.uv.index]]
+name = "pytorch-cpu"
+url = "https://download.pytorch.org/whl/cpu"
+explicit = true