Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,99 @@
+{
+  "_name_or_path": "asapp/sew-d-tiny-100k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SEWDForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    64,
+    128,
+    128,
+    128,
+    128,
+    256,
+    256,
+    256,
+    256,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    3,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "conv_stride": [
+    5,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1,
+    2,
+    1
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.65,
+  "max_position_embeddings": 512,
+  "model_type": "sew-d",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 31,
+  "num_feat_extract_layers": 13,
+  "num_hidden_layers": 12,
+  "pad_token_id": 29,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "squeeze_factor": 2,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bdd01712992d92dbd8c09fe8e2808dd6dbb74e023497c670a10a9c6e2787e7a
+size 96603525

runs/Oct20_11-15-29_5cfec6820ab9/1634728592.8331358/events.out.tfevents.1634728592.5cfec6820ab9.524.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c02ffd26f9687f18e0a960db5af52a237647ac624638c453b09cbbad0b23d2be
+size 4543

runs/Oct20_11-15-29_5cfec6820ab9/events.out.tfevents.1634728592.5cfec6820ab9.524.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd238f3e170153c4dfe84210aa0c1ff98d122c577e03a5aa5ba6335ac0f03db
+size 4799

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd7f479652b37dde0189b9002e359335983b407aa17fb7c2f98a344f6fe405b
+size 2863