Documentation changes

Author: niknah

.gitignore

@@ -163,3 +163,4 @@ cython_debug/
 #.idea/
 
 
+old/

README.md

@@ -10,6 +10,8 @@ Using F5-TTS https://github.com/SWivid/F5-TTS
 * And a .txt file of the same name with what was said.
 * Press refresh to see it in the node
 
+* `input/F5-TTS` `input/audio` folders will also work.
+
 You can use the examples here...
 * [Examples voices](examples/)
 * [Simple workflow](examples/simple_ComfyUI_F5TTS_workflow.json)
@@ -83,7 +85,8 @@ so it's becomes...
 
 ### Tips...
 
- * F5-TTS [cuts your voice sample off at 15 secs](https://github.com/SWivid/F5-TTS/blob/8898d05e374bcb8d3fc0b1286037e95df61f491f/src/f5_tts/infer/utils_infer.py#L315).
+ * F5-TTS [cuts your voice sample off at 15 secs](https://github.com/SWivid/F5-TTS/blob/8898d05e374bcb8d3fc0b1286037e95df61f491f/src/f5_tts/infer/utils_infer.py#L315).   It may cut off in the middle of a word and not cut the text only audio.   Make sure your input samples are less than 15 secs.
+ * If you're using the ComfyUI-Whisper node you will also need to install [ffmpeg](https://ffmpeg.org/download.html)
 
 
 ### Install from git
@@ -100,4 +103,4 @@ pip install -r requirements.txt
 
 ### Changes
 
-1.0.20: Added model\_type
+1.0.19: Added model\_type.

requirements.txt

@@ -22,5 +22,4 @@ wandb
 x_transformers>=1.31.14
 torch-time-stretch
 pygit2
-ffmpeg
 omegaconf