update (#83)

rwth-i6 · Jun 10, 2024 · 4be8df3 · 4be8df3
1 parent 8872168
commit 4be8df3
Show file tree

Hide file tree

Showing 5 changed files with 1,352 additions and 1 deletion.
diff --git a/2024-dynamic-encoder-size/README.md b/2024-dynamic-encoder-size/README.md
@@ -12,4 +12,6 @@ We use models parts from [i6-models](https://github.com/rwth-i6/i6_models/tree/j
 ConformerCTCModel, ConformerCTCConfig and train_step in returnn config is defined in [here](https://github.com/rwth-i6/i6_experiments/blob/main/users/jxu/experiments/ctc/tedlium2/pytorch_networks/dynamic_encoder_size/simple_topk_refactored/jointly_train_simple_top_k_layerwise.py)
 
 
-### TED-LIUM-v2 Iterative-Zero-Out
+### TED-LIUM-v2 Iterative-Zero-Out
+
+ConformerCTCModel, ConformerCTCConfig and train_step in returnn config is defined in [here](https://github.com/rwth-i6/i6_experiments/blob/main/users/jxu/experiments/ctc/tedlium2/pytorch_networks/dynamic_encoder_size/iterative_zero_out_refactored/jointly_train_iterative_zero_out_layerwise.py)