Init configs

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+onnx/model.onnx_data filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 47,
+  "[PAD]": 46
+}

config.json

@@ -0,0 +1,81 @@
+{
+  "_name_or_path": "omaryshchenko/w2v-bert-2.0-polish-CV16.0-v3",
+  "activation_dropout": 0.05,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.05,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.0,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.05,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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_prob": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 46,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.37.2",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 47,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,11 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 1,
+  "processor_class": "Wav2Vec2BertProcessor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": "<s>",
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,97 @@
+{
+    "version": "1.0",
+    "truncation": null,
+    "padding": null,
+    "added_tokens": [
+        {
+            "id": 46,
+            "content": "[PAD]",
+            "single_word": false,
+            "lstrip": true,
+            "rstrip": true,
+            "normalized": false,
+            "special": true
+        },
+        {
+            "id": 45,
+            "content": "[UNK]",
+            "single_word": false,
+            "lstrip": true,
+            "rstrip": true,
+            "normalized": false,
+            "special": true
+        }
+    ],
+    "normalizer": {
+        "type": "Replace",
+        "pattern": {
+            "String": " "
+        },
+        "content": "|"
+    },
+    "pre_tokenizer": {
+        "type": "Split",
+        "pattern": {
+            "Regex": ""
+        },
+        "behavior": "Isolated",
+        "invert": false
+    },
+    "post_processor": null,
+    "decoder": {
+        "type": "CTC",
+        "pad_token": "[PAD]",
+        "word_delimiter_token": "|",
+        "cleanup": true
+    },
+    "model": {
+        "vocab": {
+            "[PAD]": 46,
+            "[UNK]": 45,
+            "a": 1,
+            "b": 2,
+            "c": 3,
+            "ch": 40,
+            "cz": 39,
+            "d": 4,
+            "dz": 41,
+            "dzi": 44,
+            "d\u017a": 43,
+            "d\u017c": 42,
+            "e": 5,
+            "f": 6,
+            "g": 7,
+            "h": 8,
+            "i": 9,
+            "j": 10,
+            "k": 11,
+            "l": 12,
+            "m": 13,
+            "n": 14,
+            "o": 15,
+            "p": 16,
+            "q": 17,
+            "r": 18,
+            "rz": 34,
+            "s": 19,
+            "sz": 36,
+            "t": 20,
+            "u": 21,
+            "v": 22,
+            "w": 23,
+            "x": 24,
+            "y": 25,
+            "z": 26,
+            "|": 0,
+            "\u00f3": 28,
+            "\u0105": 29,
+            "\u0107": 30,
+            "\u0119": 31,
+            "\u0142": 32,
+            "\u0144": 33,
+            "\u015b": 35,
+            "\u017a": 37,
+            "\u017c": 38
+        }
+    }
+}

tokenizer_config.json

@@ -0,0 +1,104 @@
+{
+  "added_tokens_decoder": {
+    "34": {
+      "content": "rz",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "sz",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "cz",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "ch",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "dz",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "dż",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "dź",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "dzi",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2BertProcessor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,48 @@
+{
+  "[PAD]": 46,
+  "[UNK]": 45,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "ch": 40,
+  "cz": 39,
+  "d": 4,
+  "dz": 41,
+  "dzi": 44,
+  "dź": 43,
+  "dż": 42,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "rz": 34,
+  "s": 19,
+  "sz": 36,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0,
+  "ó": 28,
+  "ą": 29,
+  "ć": 30,
+  "ę": 31,
+  "ł": 32,
+  "ń": 33,
+  "ś": 35,
+  "ź": 37,
+  "ż": 38
+}