Training in progress, step 50

config.json

@@ -0,0 +1,117 @@
+{
+  "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_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": 96,
+  "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": "5.0.0",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 99,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f17e0d159e507864cd96155c7f6f4d84320e012f5d6f42ea81a32d1db7da1f4
+size 1262213332

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 sha256:322b086f3296c82722e1681d653febdca914f02d782f0e55d129a8b7e85ac20b
+size 5265

vocab.json

@@ -0,0 +1 @@
+{"\n": 0, " ": 1, "]": 2, "a": 3, "b": 4, "d": 5, "e": 6, "f": 7, "g": 8, "h": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "n": 15, "o": 16, "p": 17, "r": 18, "s": 19, "t": 20, "u": 21, "v": 22, "w": 23, "x": 24, "y": 25, "z": 26, "æ": 27, "ç": 28, "ð": 29, "ñ": 30, "ŋ": 31, "œ": 32, "ɐ": 33, "ɑ": 34, "ɒ": 35, "ɔ": 36, "ɖ": 37, "ɘ": 38, "ə": 39, "ɚ": 40, "ɛ": 41, "ɜ": 42, "ɝ": 43, "ɞ": 44, "ɡ": 45, "ɣ": 46, "ɤ": 47, "ɨ": 48, "ɪ": 49, "ɵ": 50, "ɸ": 51, "ɹ": 52, "ɻ": 53, "ɽ": 54, "ɾ": 55, "ʃ": 56, "ʈ": 57, "ʉ": 58, "ʊ": 59, "ʌ": 60, "ʒ": 61, "ʔ": 62, "ʕ": 63, "ʧ": 64, "ʰ": 65, "ʲ": 66, "ʷ": 67, "ˀ": 68, "ː": 69, "˞": 70, "ˠ": 71, "˺": 72, "̃": 73, "̆": 74, "̘": 75, "̙": 76, "̚": 77, "̜": 78, "̝": 79, "̞": 80, "̟": 81, "̠": 82, "̥": 83, "̩": 84, "̪": 85, "̬": 86, "̰": 87, "̱": 88, "̹": 89, "̻": 90, "β": 91, "θ": 92, " ": 93, "|": 94, "[UNK]": 95, "[PAD]": 96}