jbetker commited on
Commit
524ae1a
1 Parent(s): f8280e7

tortoise-detect docs

Browse files
Files changed (1) hide show
  1. README.md +15 -0
README.md CHANGED
@@ -132,6 +132,21 @@ utterances of a specific string of text. The impact of community involvement in
132
  GPT-3 or CLIP) has really surprised me. If you find something neat that you can do with Tortoise that isn't documented here,
133
  please report it to me! I would be glad to publish it to this page.
134
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
135
  ## Model architecture
136
 
137
  Tortoise TTS is inspired by OpenAI's DALLE, applied to speech data and using a better decoder. It is made up of 5 separate
 
132
  GPT-3 or CLIP) has really surprised me. If you find something neat that you can do with Tortoise that isn't documented here,
133
  please report it to me! I would be glad to publish it to this page.
134
 
135
+ ## Tortoise-detect
136
+
137
+ Out of concerns that this model might be misused, I've built a classifier that tells the likelihood that an audio clip
138
+ came from Tortoise.
139
+
140
+ This classifier can be run on any computer, usage is as follows:
141
+
142
+ ```commandline
143
+ python is_this_from_tortoise.py --clip=<path_to_suspicious_audio_file>
144
+ ```
145
+
146
+ This model has 100% accuracy on the contents of the results/ and voices/ folders in this repo. Still, treat this classifier
147
+ as a "strong signal". Classifiers can be fooled and it is likewise not impossible for this classifier to exhibit false
148
+ positives.
149
+
150
  ## Model architecture
151
 
152
  Tortoise TTS is inspired by OpenAI's DALLE, applied to speech data and using a better decoder. It is made up of 5 separate