tortoise-detect docs
Browse files
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
|