Upload 6 files

.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
+k_means.km filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,72 @@
+{
+  "_name_or_path": "langtech-veu/hubert-base-ca-5K",
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0, 
+  "transformers_version": "4.50.3",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 46
+}

k_means.km

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7738d58fdb62998d0f2253bd98fc71b7cf2bb13ca47240b92152964e491d80
+size 1538858

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": false,
+  "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:d2b4e21264b272d75511122db6e53f1a70dd0cac813e15d82c7e9d33dd935c8f
+size 377553484

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "1": {
+      "content": "<S>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "2": {
+      "content": "</S>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "3": {
+      "content": "<UNK>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<S>",
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "</S>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<UNK>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,48 @@
+{
+  "'": 5,
+  "-": 6,
+  "</S>": 2,
+  "<PAD>": 0,
+  "<S>": 1,
+  "<UNK>": 3,
+  "A": 7,
+  "B": 8,
+  "C": 9,
+  "D": 10,
+  "E": 11,
+  "F": 12,
+  "G": 13,
+  "H": 14,
+  "I": 15,
+  "J": 16,
+  "K": 17,
+  "L": 18,
+  "M": 19,
+  "N": 20,
+  "O": 21,
+  "P": 22,
+  "Q": 23,
+  "R": 24,
+  "S": 25,
+  "T": 26,
+  "U": 27,
+  "V": 28,
+  "W": 29,
+  "X": 30,
+  "Y": 31,
+  "Z": 32,
+  "|": 4,
+  "·": 44,
+  "À": 33,
+  "Á": 34,
+  "Ç": 35,
+  "È": 36,
+  "É": 37,
+  "Í": 38,
+  "Ï": 39,
+  "Ñ": 40,
+  "Ò": 41,
+  "Ó": 42,
+  "Ú": 43,
+  "Ü": 45
+}