diff --git a/akk.md b/akk.md
new file mode 100644
index 0000000..8d2380a
--- /dev/null
+++ b/akk.md
@@ -0,0 +1,24 @@
+# akk.traineddata
+
+## Model card
+
+* Language - Akkadian
+* Language code - akk
+* Type of training - finetuning for LSTM models, training for legacy model
+* Contributed by - [@Shreeshrii](https://github.com/Shreeshrii) and [@wincentbalin](https://github.com/wincentbalin)
+
+## Model files
+
+* LSTM model - [akk.traineddata](best/akk.traineddata)
+* Fast LSTM model - [akk.traineddata](fast/akk.traineddata)
+* Legacy model - [akk.traineddata](legacy/akk.traineddata)
+
+## Training Procedure 
+
+Training was performed by [@Shreeshrii](https://github.com/Shreeshrii) and [@wincentbalin](https://github.com/wincentbalin).
+
+The source data for the LSTM model is provided in the [LSTM langdata](https://github.com/tesseract-ocr/langdata_lstm/tree/main/akk)
+repository and for the legacy model in the [legacy langdata](https://github.com/tesseract-ocr/langdata/tree/main/akk) repository.
+
+The description of the training procedure is provided in the [tesstrain wiki](https://github.com/tesseract-ocr/tesstrain/wiki/Akkadian-Cuneiform). The repository with the most recent setup is [here](https://github.com/wincentbalin/tesstrain-akk).
+
diff --git a/akk/best/akk.traineddata b/akk/best/akk.traineddata
new file mode 100644
index 0000000..8aa340c
Binary files /dev/null and b/akk/best/akk.traineddata differ
diff --git a/akk/fast/akk.traineddata b/akk/fast/akk.traineddata
new file mode 100644
index 0000000..e840dc9
Binary files /dev/null and b/akk/fast/akk.traineddata differ
diff --git a/akk/legacy/akk.traineddata b/akk/legacy/akk.traineddata
new file mode 100644
index 0000000..d6865d1
Binary files /dev/null and b/akk/legacy/akk.traineddata differ