1. unify env for TTS and ASR; 2. avoid transformers 5.0.0 temporarily

docs/vibevoice-asr.md

@@ -65,7 +65,8 @@ sudo docker run --privileged --net=host --ipc=host --ulimit memlock=-1:-1 --ulim
 ```bash
 git clone https://github.com/microsoft/VibeVoice.git
 cd VibeVoice
-pip install -e .[asr]
+
+pip install -e .
 ```
 
 ## Usages

docs/vibevoice-realtime-0.5b.md

@@ -97,9 +97,10 @@ sudo docker run --privileged --net=host --ipc=host --ulimit memlock=-1:-1 --ulim
 git clone https://github.com/microsoft/VibeVoice.git
 cd VibeVoice/
 
-pip install -e .[tts]
+pip install -e .
 ```
 
+
 ## Usages
 
 

finetuning-asr/README.md

@@ -5,8 +5,8 @@ This directory contains scripts for LoRA (Low-Rank Adaptation) fine-tuning of th
 ## Requirements
 
 ```bash
-# you need to install vibevoice first
-# pip install -e .[asr]
+# Install vibevoice first
+pip install -e .
 
 pip install peft
 ```

pyproject.toml

@@ -18,6 +18,7 @@ classifiers = [
 ]
 dependencies = [
     "torch",
+    "transformers>=4.51.3,<5.0.0",
     "accelerate",
     "llvmlite>=0.40.0",
     "numba>=0.57.0",
@@ -29,27 +30,12 @@ dependencies = [
     "ml-collections",
     "absl-py",
     "gradio",
-]
-
-[project.optional-dependencies]
-tts = [
-  "transformers==4.51.3", # we develop this project on transformers==4.51.3, later version may not be compatible
-  "av",
-  "aiortc",
-  "uvicorn[standard]",
-  "fastapi"
-]
-
-asr = [
-  "transformers>=4.51.3", # the versions after 4.51.3 are all support
-  "pydub" # for visualization
-]
-
-vllm = [
-  "transformers>=4.51.3",
-  "fastapi",
-  "uvicorn[standard]",
-  "requests",
+    "av",
+    "aiortc",
+    "uvicorn[standard]",
+    "fastapi",
+    "pydub",
+    "requests",
 ]
 
 [project.entry-points."vllm.general_plugins"]