readme

README.md

@@ -6,11 +6,14 @@ language:
 metrics:
 - wer
 ---
+
+Internal model alias name:
 `v6-relPosAttDef-noBias-aedLoss-bhv20-11gb-f32-bs15k-accgrad1-mgpu4-pavg100-wd1e_2-lrlin1e_5_295k-featBN-speedpertV2-spm10k-bpeSample001`
 
-https://github.com/rwth-i6/i6_experiments
+From https://github.com/rwth-i6/i6_experiments
 `i6_experiments/users/zeyer/experiments/exp2024_04_23_baselines/ctc.py`
 
+This Sisyphus config code snippet:
 ```
     # v6-relPosAttDef-noBias-aedLoss-bhv20-11gb-f32-bs15k-accgrad1-mgpu4-pavg100-wd1e_2-lrlin1e_5_295k-featBN-speedpertV2-spm10k-bpeSample001
     # noBias. (Baseline: 5.77)
@@ -40,4 +43,11 @@ https://github.com/rwth-i6/i6_experiments
         vocab="spm10k",
         train_vocab_opts={"other_opts": {"class": "SamplingBytePairEncoding", "breadth_prob": 0.01}},
     )
-```
+```
+
+I uploaded the `info` and `output` files from the Sisyphus RETURNN training job to `trainjob`,
+except of the model checkpoint, which I uploaded to `data`.
+
+From the train job `info` file, I was checking dependencies.
+Specifically, there is the SPM vocab.
+I uploaded those to `deps`.