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": 65,
+  "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": 68,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fd702890781e1edfb8245c98440039556fd7c48675f6668635bf4771188f12
+size 1262086280

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 sha256:6ac2916944b886c31c6662e2b408b6834e03288686db39e94edb724618c75938
+size 6033

vocab.json

@@ -0,0 +1 @@
+{"e": 0, "\u0300": 1, "k": 2, "n": 3, "\u00ea": 4, "\u0289": 5, "y": 6, "w": 7, "\u00e9": 8, "\u00e0": 9, "\u030c": 10, "\u0159": 11, "\u01d0": 12, "\u01d4": 13, "\u0155": 14, "\u01d2": 15, "i": 16, "l": 17, "\u00ec": 18, "\u0268": 19, "f": 20, "r": 22, "\u017a": 23, "\u00f9": 24, "\u00f4": 25, "s": 26, "`": 27, "o": 28, "\u00e8": 29, "\u011b": 30, "\u014b": 31, "j": 32, "\u0111": 33, "d": 34, "\u00e1": 35, "\u00fb": 36, "z": 37, "x": 38, "\u1e81": 39, "\u015b": 40, "\u0302": 41, "h": 42, "t": 43, "\u00f3": 44, "m": 45, "a": 46, "p": 47, "\u0161": 48, "u": 49, "b": 50, "\u00ee": 51, "'": 52, "v": 53, "\u0266": 54, "\u017e": 55, "\u00ed": 56, "\u1e91": 57, "g": 58, "\u00f2": 59, "c": 60, "\u00fa": 61, "\u01ce": 62, "\u00e2": 63, "|": 21, "[UNK]": 64, "[PAD]": 65}