Upload data

1. Trained word-level LSTM.
2. Trained token-level 4-gram arpa model.
3. Fine-tuned gpt2 model.
4. Baseline ASR model (https://catalog.ngc.nvidia.com/orgs/nvidia/teams/nemo/models/stt_en_conformer_transducer_small).
5. LibriSpeech text data for train, validation and test.

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+asr/stt_en_conformer_transducer_small.nemo filter=lfs diff=lfs merge=lfs -text
+text/librispeech/clean_train.360.txt filter=lfs diff=lfs merge=lfs -text
+text/librispeech/other_train.500.txt filter=lfs diff=lfs merge=lfs -text
+text/lstm/train.txt filter=lfs diff=lfs merge=lfs -text
+text/ngram/train.txt filter=lfs diff=lfs merge=lfs -text

asr/stt_en_conformer_transducer_small.nemo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9894f37bb36b183590776dbd000d590889582f188b8bfa63fa795205a0ec0b8e
+size 54480175

gpt2/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1024,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 1025,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "pad_token_id": 1026,
+  "predict_special_tokens": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.2",
+  "use_cache": true,
+  "vocab_size": 1027
+}

gpt2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7884f6ef1acccf72b84d2d7b7ad167b2484183dde8e89b7960dce581a1c16f
+size 1242923293

gpt2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f31c43de1a0b0f9b6421842529cc6b64e1949d34e9fc4bbd1ce7118bdea43c
+size 3323

kenlm/4_ngram_output.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da61a874bed41087e90c8b60838ba8656356a040ced4f6fc34bffa04e11ce4d8
+size 78345492

lstm/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb09c452264e0bd81116dcd08922b57163ae4d20423dbe3ce60182906017de5c
+size 194079513

lstm/tokenizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99a3302dc2da750175a801711394769976331ec8f658f8acc6a60021db0151bf
+size 2030227

text/librispeech/clean_train.360.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc83220078f2898311f0e0ba68bba6a1681d5b1c08ba0253e6672f85b53dfb38
+size 19225281

text/librispeech/other_train.500.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c0736d55a7492da63c126f8c84527ea1af199119771f1000a06b66b7ea9e837
+size 25539815

text/lstm/train.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21aa7b62b4c182b51114021427dffcad142c35a327de62b343bb240c5dd62c6
+size 45017800

text/ngram/train.txt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ec40af82e5ff8e35ab249f3a5525894d20f41e4110df85c8e1746896069cd1
+size 44765096