Upload model

config.json

@@ -0,0 +1,98 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "SEWDForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "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": 0.0,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 64,
+  "mask_feature_prob": 0.5,
+  "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": 8,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 31,
+  "num_feat_extract_layers": 13,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "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:e499fc6f87d88b38110d6680fe02711ddecc2c835baa2d66b25ead0942e30542
+size 315434249

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

@@ -0,0 +1 @@
+{"<s>": 1, "<pad>": 0, "</s>": 2, "<unk>": 3, "|": 4, "E": 5, "T": 6, "A": 7, "O": 8, "N": 9, "I": 10, "H": 11, "S": 12, "R": 13, "D": 14, "L": 15, "U": 16, "M": 17, "W": 18, "C": 19, "F": 20, "G": 21, "Y": 22, "P": 23, "B": 24, "V": 25, "K": 26, "'": 27, "X": 28, "J": 29, "Q": 30, "Z": 31}