Training in progress, step 5000

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "</s>": 70,
+  "<s>": 69
+}

config.json

@@ -0,0 +1,116 @@
+{
+  "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": 69,
+  "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": 70,
+  "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,
+  "gradient_checkpointing": false,
+  "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": 0,
+  "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": "4.56.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 71,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6301b948a5d62d9b6fa535e2855edf49d35d5f5ec8e0627f8211be3ed8312f7d
+size 1262098580

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "70": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80a614129f3718ed58ab554a3df03c4eef833b4fd82818373d36fee1771b79a8
+size 5777

vocab.json

@@ -0,0 +1,71 @@
+{
+  "#": 2,
+  "$": 3,
+  "'": 4,
+  "*": 5,
+  "+": 6,
+  "0": 7,
+  "1": 8,
+  "2": 9,
+  "3": 10,
+  "4": 11,
+  "5": 12,
+  "6": 13,
+  "7": 14,
+  "8": 15,
+  "9": 16,
+  "=": 17,
+  "@": 18,
+  "[PAD]": 0,
+  "[UNK]": 68,
+  "^": 19,
+  "a": 20,
+  "b": 21,
+  "c": 22,
+  "d": 23,
+  "e": 24,
+  "f": 25,
+  "g": 26,
+  "h": 27,
+  "i": 28,
+  "j": 29,
+  "k": 30,
+  "l": 31,
+  "m": 32,
+  "n": 33,
+  "o": 34,
+  "p": 35,
+  "q": 36,
+  "r": 37,
+  "s": 38,
+  "t": 39,
+  "u": 40,
+  "v": 41,
+  "w": 42,
+  "x": 43,
+  "y": 44,
+  "z": 45,
+  "|": 1,
+  "²": 46,
+  "¹": 47,
+  "¼": 48,
+  "â": 49,
+  "ä": 50,
+  "ç": 51,
+  "è": 52,
+  "é": 53,
+  "î": 54,
+  "ö": 55,
+  "÷": 56,
+  "û": 57,
+  "ü": 58,
+  "ğ": 59,
+  "ı": 60,
+  "ń": 61,
+  "ō": 62,
+  "ş": 63,
+  "̇": 64,
+  "–": 65,
+  "∆": 66,
+  "√": 67
+}