Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,116 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "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_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 56,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 57,
+  "xvector_output_dim": 512
+}

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 sha256:3943f4eab668b9e144d58433dd46c6bc12afad06a7f430aff95c96a2a562b614
+size 1262135533

runs/Aug30_10-50-50_arkark/events.out.tfevents.1693407100.arkark.357915.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fa2827cc27a3f772ba21791869cf193de3302b62bd533a0c4bf881206383d8d
+size 341

runs/Aug30_10-55-14_arkark/events.out.tfevents.1693407361.arkark.359400.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de44a8efa9cbe2139df608bc20a0ee37888e0bd2db24472c295903e94db7f01
+size 341

runs/Aug30_11-03-16_arkark/events.out.tfevents.1693407846.arkark.362180.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6585bdc04de003a321237258028068dd921243c03d10e29ae489db6df922f59c
+size 5729

runs/Aug30_11-06-27_arkark/events.out.tfevents.1693408036.arkark.363572.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f5bd710c688d729962be02f9b304b1692893136e82500444cf365b66442fef0
+size 6204

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7585f2f896559b400a77acb2c32a230c7b4551a94126209ae89272137ea378c8
+size 3963

vocab.json

@@ -0,0 +1 @@
+{"C": 1, "J": 2, "O": 3, "P": 4, "S": 5, "W": 6, "Y": 7, "b": 8, "d": 9, "e": 10, "f": 11, "g": 12, "h": 13, "i": 14, "j": 15, "k": 16, "l": 17, "m": 18, "n": 19, "o": 20, "p": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "z": 27, "\u00e6": 28, "\u00f0": 29, "\u014b": 30, "\u0251": 31, "\u0254": 32, "\u0259": 33, "\u025a": 34, "\u025b": 35, "\u025d": 36, "\u0261": 37, "\u0266": 38, "\u0268": 39, "\u026a": 40, "\u0279": 41, "\u027e": 42, "\u0283": 43, "\u0289": 44, "\u028a": 45, "\u028c": 46, "\u0292": 47, "\u0294": 48, "\u0303": 49, "\u030d": 50, "\u031a": 51, "\u0325": 52, "\u0329": 53, "\u03b8": 54, "|": 0, "[UNK]": 55, "[PAD]": 56}

wav2vec2-base-timit-demo-retrain_vocab_20230830_1106.json

@@ -0,0 +1 @@
+{"C": 1, "J": 2, "O": 3, "P": 4, "S": 5, "W": 6, "Y": 7, "b": 8, "d": 9, "e": 10, "f": 11, "g": 12, "h": 13, "i": 14, "j": 15, "k": 16, "l": 17, "m": 18, "n": 19, "o": 20, "p": 21, "s": 22, "t": 23, "u": 24, "v": 25, "w": 26, "z": 27, "\u00e6": 28, "\u00f0": 29, "\u014b": 30, "\u0251": 31, "\u0254": 32, "\u0259": 33, "\u025a": 34, "\u025b": 35, "\u025d": 36, "\u0261": 37, "\u0266": 38, "\u0268": 39, "\u026a": 40, "\u0279": 41, "\u027e": 42, "\u0283": 43, "\u0289": 44, "\u028a": 45, "\u028c": 46, "\u0292": 47, "\u0294": 48, "\u0303": 49, "\u030d": 50, "\u031a": 51, "\u0325": 52, "\u0329": 53, "\u03b8": 54, "|": 0, "[UNK]": 55, "[PAD]": 56}