Training in progress, step 1000

.gitignore

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

config.json

@@ -0,0 +1,91 @@
+{
+  "_name_or_path": "lgris/sew-tiny-pt",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SEWForCTC"
+  ],
+  "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": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.05,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.65,
+  "model_type": "sew",
+  "num_attention_heads": 8,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 31,
+  "num_feat_extract_layers": 13,
+  "num_hidden_layers": 12,
+  "pad_token_id": 47,
+  "squeeze_factor": 2,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 50
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ac3148349118b2540185ae05a16f348462f2c9da364a5b8ced85d739b24194
+size 163023563

runs/Jan28_01-38-28_job-aa846e50-242e-4547-af03-321d0eb3e719/1643333919.9825568/events.out.tfevents.1643333919.job-aa846e50-242e-4547-af03-321d0eb3e719.4011584.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e52a6cc9f8b1d4d1fd02b6243f98b931d87ef21433b0adf276e52d14227bdb89
+size 4811

runs/Jan28_01-38-28_job-aa846e50-242e-4547-af03-321d0eb3e719/events.out.tfevents.1643333919.job-aa846e50-242e-4547-af03-321d0eb3e719.4011584.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3330516a88a43b855cceea2fa94838aba7f2ffce26cc6626aebe0d249f2d3380
+size 4639

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d84d62a11caffaa490685f9635662b82ad1d7e5dad37cd43c63e6eb6eaca6f6
+size 3055