Upload 8 files

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 41,
+  "<s>": 40
+}

config.json

@@ -0,0 +1,115 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "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_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 33,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.57.6",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 40,
+  "xvector_output_dim": 512
+}

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:127a831b4c63d62d041b0fed9edc93774d8a9ef95137884b1be1bc0d8da14b1d
+size 356278039

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer.json

@@ -0,0 +1,107 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 21,
+      "content": "[UNK]",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 33,
+      "content": "[PAD]",
+      "single_word": false,
+      "lstrip": true,
+      "rstrip": true,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 40,
+      "content": "<s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 41,
+      "content": "</s>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "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": {
+    "type": "WordLevel",
+    "vocab": {
+      " ": 22,
+      "[PAD]": 33,
+      "[UNK]": 21,
+      "a": 3,
+      "b": 14,
+      "d": 19,
+      "e": 13,
+      "f": 20,
+      "h": 30,
+      "i": 38,
+      "j": 9,
+      "k": 1,
+      "l": 39,
+      "m": 24,
+      "n": 29,
+      "o": 2,
+      "p": 12,
+      "s": 8,
+      "t": 16,
+      "u": 11,
+      "v": 17,
+      "w": 34,
+      "z": 35,
+      "æ": 4,
+      "ð": 28,
+      "ŋ": 7,
+      "ɑ": 0,
+      "ɔ": 36,
+      "ɚ": 32,
+      "ɛ": 15,
+      "ɡ": 37,
+      "ɪ": 18,
+      "ɹ": 23,
+      "ʃ": 5,
+      "ʊ": 10,
+      "ʌ": 31,
+      "ʒ": 25,
+      "ˌ": 26,
+      "͡": 6,
+      "θ": 27,
+      "</s>": 41,
+      "<s>": 40
+    },
+    "unk_token": "[UNK]"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,49 @@
+{
+  "added_tokens_decoder": {
+    "21": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "41": {
+      "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>",
+  "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 +1,42 @@
+{
+  " ": 22,
+  "[PAD]": 33,
+  "[UNK]": 21,
+  "a": 3,
+  "b": 14,
+  "d": 19,
+  "e": 13,
+  "f": 20,
+  "h": 30,
+  "i": 38,
+  "j": 9,
+  "k": 1,
+  "l": 39,
+  "m": 24,
+  "n": 29,
+  "o": 2,
+  "p": 12,
+  "s": 8,
+  "t": 16,
+  "u": 11,
+  "v": 17,
+  "w": 34,
+  "z": 35,
+  "æ": 4,
+  "ð": 28,
+  "ŋ": 7,
+  "ɑ": 0,
+  "ɔ": 36,
+  "ɚ": 32,
+  "ɛ": 15,
+  "ɡ": 37,
+  "ɪ": 18,
+  "ɹ": 23,
+  "ʃ": 5,
+  "ʊ": 10,
+  "ʌ": 31,
+  "ʒ": 25,
+  "ˌ": 26,
+  "͡": 6,
+  "θ": 27
+}