Training in progress, step 200

config.json

@@ -0,0 +1,107 @@
+{
+  "activation_dropout": 0.05,
+  "adapter_attn_dim": 16,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 0.05,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "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": 0.05,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1280,
+  "pad_token_id": 112,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "4.57.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 115,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be614c7f57988ff1da1b408514cd2344f67efff3f87654feeb9b21ed8f2b00ff
+size 3859321340

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": true,
+  "sampling_rate": 16000
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7ce494612c9b784420008388cca0fecbfe71c7d1f6a9bd2b6384dc50204f5eb
+size 6033

vocab.json

@@ -1,117 +1 @@
-{
-  "led": {
-    "'": 7,
-    "[PAD]": 112,
-    "[UNK]": 111,
-    "`": 37,
-    "a": 86,
-    "b": 76,
-    "bb": 70,
-    "c": 36,
-    "ch": 31,
-    "d": 110,
-    "dd": 12,
-    "dh": 17,
-    "dj": 89,
-    "dr": 34,
-    "dy": 81,
-    "dz": 19,
-    "e": 98,
-    "ey": 20,
-    "f": 67,
-    "g": 75,
-    "gb": 107,
-    "h": 11,
-    "i": 99,
-    "iy": 44,
-    "j": 21,
-    "k": 45,
-    "kp": 79,
-    "l": 104,
-    "m": 33,
-    "mb": 62,
-    "n": 22,
-    "nd": 97,
-    "ndr": 23,
-    "ng": 29,
-    "ngb": 9,
-    "nj": 39,
-    "ny": 10,
-    "nz": 80,
-    "o": 46,
-    "ow": 85,
-    "p": 109,
-    "pb": 100,
-    "r": 88,
-    "r̀": 68,
-    "ŕ": 54,
-    "ř": 53,
-    "s": 14,
-    "sh": 105,
-    "t": 5,
-    "td": 2,
-    "tdr": 43,
-    "tdy": 82,
-    "th": 56,
-    "ts": 84,
-    "u": 101,
-    "uw": 27,
-    "v": 51,
-    "w": 32,
-    "x": 87,
-    "y": 35,
-    "z": 47,
-    "z̀": 38,
-    "ź": 83,
-    "ž": 71,
-    "|": 0,
-    "à": 28,
-    "á": 8,
-    "â": 77,
-    "è": 69,
-    "èy": 49,
-    "é": 55,
-    "éy": 108,
-    "ê": 24,
-    "ì": 26,
-    "ìy": 91,
-    "í": 25,
-    "íy": 52,
-    "î": 73,
-    "ò": 59,
-    "òw": 103,
-    "ó": 90,
-    "ów": 64,
-    "ô": 42,
-    "ù": 1,
-    "ùw": 18,
-    "ú": 6,
-    "úw": 3,
-    "û": 66,
-    "đ": 106,
-    "ě": 30,
-    "ěy": 4,
-    "ŋ": 78,
-    "ŕ": 40,
-    "ř": 92,
-    "ś": 61,
-    "š": 15,
-    "ź": 65,
-    "ž": 41,
-    "ǎ": 96,
-    "ǐ": 50,
-    "ǐy": 95,
-    "ǒ": 57,
-    "ǒw": 74,
-    "ǔ": 60,
-    "ǔw": 48,
-    "ɦ": 58,
-    "ɨ": 13,
-    "ʉ": 93,
-    "̀": 94,
-    "̂": 72,
-    "̌": 102,
-    "ẁ": 16,
-    "ẑ": 63
-  }
-}
+{"led": {"\u00f9": 1, "td": 2, "\u00faw": 3, "\u011by": 4, "t": 5, "\u00fa": 6, "'": 7, "\u00e1": 8, "ngb": 9, "ny": 10, "h": 11, "dd": 12, "\u0268": 13, "s": 14, "\u0161": 15, "\u1e81": 16, "dh": 17, "\u00f9w": 18, "dz": 19, "ey": 20, "j": 21, "n": 22, "ndr": 23, "\u00ea": 24, "\u00ed": 25, "\u00ec": 26, "uw": 27, "\u00e0": 28, "ng": 29, "\u011b": 30, "ch": 31, "w": 32, "m": 33, "dr": 34, "y": 35, "c": 36, "`": 37, "z\u0300": 38, "nj": 39, "\u0155": 40, "\u017e": 41, "\u00f4": 42, "tdr": 43, "iy": 44, "k": 45, "o": 46, "z": 47, "\u01d4w": 48, "\u00e8y": 49, "\u01d0": 50, "v": 51, "\u00edy": 52, "r\u030c": 53, "r\u0301": 54, "\u00e9": 55, "th": 56, "\u01d2": 57, "\u0266": 58, "\u00f2": 59, "\u01d4": 60, "\u015b": 61, "mb": 62, "\u1e91": 63, "\u00f3w": 64, "\u017a": 65, "\u00fb": 66, "f": 67, "r\u0300": 68, "\u00e8": 69, "bb": 70, "z\u030c": 71, "\u0302": 72, "\u00ee": 73, "\u01d2w": 74, "g": 75, "b": 76, "\u00e2": 77, "\u014b": 78, "kp": 79, "nz": 80, "dy": 81, "tdy": 82, "z\u0301": 83, "ts": 84, "ow": 85, "a": 86, "x": 87, "r": 88, "dj": 89, "\u00f3": 90, "\u00ecy": 91, "\u0159": 92, "\u0289": 93, "\u0300": 94, "\u01d0y": 95, "\u01ce": 96, "nd": 97, "e": 98, "i": 99, "pb": 100, "u": 101, "\u030c": 102, "\u00f2w": 103, "l": 104, "sh": 105, "\u0111": 106, "gb": 107, "\u00e9y": 108, "p": 109, "d": 110, "|": 0, "[UNK]": 111, "[PAD]": 112}}