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": 47,
+  "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": 50,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e170227a06a86bc5b61bb5fc8c35e69892abb951479d63b404bd7c737c98c506
+size 3858988280

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:cf9003781d75a027e5a62393df5460165f44e4addb391f90a762c496029b556d
+size 6033

vocab.json

@@ -1,52 +1 @@
-{
-  "aln": {
-    "'": 15,
-    "[PAD]": 47,
-    "[UNK]": 46,
-    "a": 39,
-    "b": 41,
-    "c": 18,
-    "d": 3,
-    "dh": 19,
-    "e": 2,
-    "f": 27,
-    "g": 31,
-    "gj": 16,
-    "h": 43,
-    "i": 0,
-    "j": 42,
-    "k": 4,
-    "l": 5,
-    "ll": 1,
-    "m": 36,
-    "n": 25,
-    "nj": 14,
-    "o": 10,
-    "p": 24,
-    "q": 11,
-    "r": 13,
-    "rr": 28,
-    "s": 35,
-    "sh": 20,
-    "t": 30,
-    "th": 45,
-    "u": 33,
-    "v": 7,
-    "w": 12,
-    "x": 29,
-    "xh": 17,
-    "y": 32,
-    "z": 22,
-    "zh": 8,
-    "|": 21,
-    "ά": 6,
-    "έ": 44,
-    "α": 37,
-    "ε": 34,
-    "κ": 40,
-    "ν": 9,
-    "π": 38,
-    "σ": 26,
-    "τ": 23
-  }
-}
+{"aln": {"i": 0, "ll": 1, "e": 2, "d": 3, "k": 4, "l": 5, "\u03ac": 6, "v": 7, "zh": 8, "\u03bd": 9, "o": 10, "q": 11, "w": 12, "r": 13, "nj": 14, "'": 15, "gj": 16, "xh": 17, "c": 18, "dh": 19, "sh": 20, "z": 22, "\u03c4": 23, "p": 24, "n": 25, "\u03c3": 26, "f": 27, "rr": 28, "x": 29, "t": 30, "g": 31, "y": 32, "u": 33, "\u03b5": 34, "s": 35, "m": 36, "\u03b1": 37, "\u03c0": 38, "a": 39, "\u03ba": 40, "b": 41, "j": 42, "h": 43, "\u03ad": 44, "th": 45, "|": 21, "[UNK]": 46, "[PAD]": 47}}