fix #1239, use gradio>=6.0; add more clear instruction for ffmpeg installation (#1234)

Author: Yushen Chen

README.md

@@ -30,6 +30,9 @@
 # Create a conda env with python_version>=3.10  (you could also use virtualenv)
 conda create -n f5-tts python=3.11
 conda activate f5-tts
+
+# Install FFmpeg if you haven't yet
+conda install ffmpeg
 ```
 
 ### Install PyTorch with matched device
@@ -39,7 +42,11 @@ conda activate f5-tts
 
 > ```bash
 > # Install pytorch with your CUDA version, e.g.
+> pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 --extra-index-url https://download.pytorch.org/whl/cu128
+> 
+> # And also possible previous versions, e.g.
 > pip install torch==2.4.0+cu124 torchaudio==2.4.0+cu124 --extra-index-url https://download.pytorch.org/whl/cu124
+> # etc.
 > ```
 
 </details>

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "f5-tts"
-version = "1.1.10"
+version = "1.1.11"
 description = "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"
 readme = "README.md"
 license = {text = "MIT License"}
@@ -20,7 +20,7 @@ dependencies = [
     "click",
     "datasets",
     "ema_pytorch>=0.5.2",
-    "gradio>=5.0.0",
+    "gradio>=6.0.0",
     "hydra-core>=1.3.0",
     "librosa",
     "matplotlib",

src/f5_tts/infer/infer_gradio.py

@@ -577,7 +577,7 @@ def insert_speech_type_fn(current_text, speech_type_name, speech_type_seed, spee
         label="Cherry-pick Interface",
         lines=10,
         max_lines=40,
-        show_copy_button=True,
+        buttons=["copy"],  # show_copy_button=True if gradio<6.0
         interactive=False,
         visible=False,
     )