Training in progress, step 100

config.json

@@ -0,0 +1,108 @@
+{
+  "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": 0.0,
+  "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,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 80,
+  "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": "4.57.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 81,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780ad213b44fd64ecb2f72e90514ae3147c4c07bcf9c874ffa1a51de86115ba0
+size 1262139580

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:d625f0bbca6152d277f9ecd7de01c1b7f5b77c30b1f624769c96b6bfac27e718
+size 6033

vocab.json

@@ -0,0 +1 @@
+{"x": 0, "\"": 1, "Y": 2, "a": 3, "e": 4, "P": 5, "L": 6, "g": 7, "K": 8, "'": 9, "w": 10, "p": 11, "}": 12, "l": 13, "u": 14, "[": 15, "Z": 16, " ": 17, "\u03c4": 18, "A": 19, "y": 20, "\u03ba": 21, "k": 22, "j": 23, "\u03ac": 24, "\u03b1": 25, "q": 26, "n": 27, "\u03ad": 28, "\u03b5": 29, "B": 30, "N": 31, "o": 32, ",": 33, "X": 34, "\u03bd": 35, "\u03c0": 36, "\u03c3": 37, "F": 38, "T": 39, "!": 40, "I": 41, "h": 42, "J": 43, "W": 44, "z": 45, "O": 46, "(": 47, "d": 48, "]": 49, "R": 50, "m": 51, "-": 52, "D": 53, "{": 54, "i": 55, "c": 56, "v": 57, ")": 58, "U": 59, "f": 60, "G": 61, "t": 62, "M": 63, "r": 64, "H": 65, "S": 66, ".": 67, "E": 68, "s": 69, "b": 70, ":": 71, "C": 72, "Q": 73, "V": 74, "?": 75, "|": 76}