first model

.gitattributes

@@ -14,3 +14,4 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+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-1/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 sha256:7a10b2b85ea22b75682b79a47875be69495f7b514755cb37e0c3c7158aa739aa
+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-1/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/data/models/wav2vec2-sid-voxforge-cetuc-1"}

vocab.json

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