add tokenizer

config.json

@@ -0,0 +1,88 @@
+{
+  "_name_or_path": "facebook/wav2vec2-base",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_attention_heads": 12,
+  "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": 12,
+  "num_negatives": 100,
+  "pad_token_id": 29,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "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": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a208d7c94b21df09bc933bb6becf04653c497fa49b1c5d464bbf8dcd420932ee
+size 377670039

runs/Feb19_11-52-31_speechlab/1645251933.2814476/events.out.tfevents.1645251933.speechlab.24101.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b09ebbcf0840fa5896f2592f674822302fe37dcf569c6d83593bd9de0c4df53
+size 4552

runs/Feb19_11-52-31_speechlab/events.out.tfevents.1645251933.speechlab.24101.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:393164d332159b2a584a727b1dddcd9267e607596ea311964008fa215a862517
+size 18590

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:579f3d96bf6dc80abaeb27c4918cda5bb29b32349220a4f20786e7fb2d4e8c93
+size 2863

vocab.json

@@ -1 +1 @@
-{"q": 0, "s": 1, "e": 2, "t": 3, "h": 4, "b": 5, "p": 6, "a": 7, "j": 8, "f": 9, "o": 10, "u": 11, "k": 12, "i": 13, "w": 14, "r": 15, "'": 16, "z": 17, "y": 18, "v": 19, "x": 20, "c": 21, "d": 23, "m": 24, "g": 25, "l": 26, "n": 27, "|": 22, "[UNK]": 28, "[PAD]": 29}
+{"h": 0, "q": 1, "z": 2, "i": 3, "a": 5, "w": 6, "u": 7, "j": 8, "e": 9, "'": 10, "l": 11, "v": 12, "s": 13, "x": 14, "p": 15, "r": 16, "k": 17, "y": 18, "m": 19, "b": 20, "d": 21, "t": 22, "n": 23, "f": 24, "c": 25, "o": 26, "g": 27, "|": 4, "[UNK]": 28, "[PAD]": 29}