Update README.md

README.md

@@ -10,9 +10,9 @@ license_link: LICENSE
 
 # Getting started
 
-If you are a biologist looking to get started with MegaDetector, you probably don't want to download the model directly; instead, check out [AddaxAI](https://addaxdatascience.com/addaxai/) (formerly EcoAssist), a GUI-based tool for running AI models on camera trap images.
+If you are a biologist looking to get started with MegaDetector, you probably don't want to download the model directly; instead, check out [AddaxAI](https://addaxdatascience.com/addaxai/), a GUI-based tool for running AI models on camera trap images.
 
-If you want to run MegaDetector directly, check out the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md) and the [MegaDetector Python package](https://megadetector.readthedocs.io/).
+If you want to run MegaDetector directly (at the command line, or from code), check out the [MegaDetector User Guide](https://github.com/agentmorris/MegaDetector/blob/main/megadetector.md) and the [MegaDetector Python package](https://megadetector.readthedocs.io/).
 
 # Variations
 
@@ -24,15 +24,15 @@ Three variations of the model are included in this Hugging Face release:
   
 All three variations use the same architecture (YOLOv5x6).
 
-More information about how these models are related, along with links to other variants that are available but not recommended for general use, is available in the [MDv1000 release notes](https://github.com/agentmorris/MegaDetector/blob/main/docs/release-notes/mdv1000-release.md#introducing-mdv1000).
+More information about how these models are related, along with information about other variants that are available but not recommended for general use, is available in the [MDv1000 release notes](https://github.com/agentmorris/MegaDetector/blob/main/docs/release-notes/mdv1000-release.md#introducing-mdv1000).
 
 # License information
 
 MegaDetector-specific code is MIT-licensed.
 
-The most restrictive license among the inference-time dependencies is GPL.
+The most restrictive license among inference-time dependencies is GPL.
 
-Training data is provided under a combination of CDLA-permissive (for public data from [LILA](https://lila.science)) and a proprietary licenses (for private data).  None of the training data licenses place any restrictions on the use of the model.
+Training data was provided under a combination of CDLA-permissive (for public data from [LILA](https://lila.science)) and proprietary licenses (for private data).  None of the training data licenses place any restrictions on the use of the model.
 
 # Sample output