first version

.gitattributes

@@ -0,0 +1 @@
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 54, "</s>": 55}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "/data/models/wav2vec2-sid-voxforge-cetuc-2/checkpoint-26400",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "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_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",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 53,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 54
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd611d0e633ff223e615c92eee806f019d9cee618157e1d3ce6ddfa212e24085
+size 1262149335

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": "|", "special_tokens_map_file": "/data/models/wav2vec2-sid-voxforge-cetuc-2/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/data/models/wav2vec2-sid-voxforge-cetuc-2"}

vocab.json

@@ -0,0 +1 @@
+{"ã": 0, "q": 1, "è": 2, "g": 3, "t": 4, "é": 5, "u": 6, "0": 7, "2": 8, "3": 9, "à": 10, "ì": 11, "z": 12, "h": 13, "ê": 14, "”": 15, "'": 16, "ç": 18, "c": 19, "á": 20, "w": 21, "b": 22, "k": 23, "m": 24, "4": 25, "v": 26, "ô": 27, "a": 28, "i": 29, "p": 30, "y": 31, "9": 32, "e": 33, "â": 34, "õ": 35, "s": 36, "n": 37, "1": 38, "ú": 39, "x": 40, "j": 41, "l": 42, "6": 43, "o": 44, "ó": 45, "5": 46, "r": 47, "f": 48, "ü": 49, "d": 50, "í": 51, "|": 17, "[UNK]": 52, "[PAD]": 53}