Training in progress, step 400

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 101,
+  "<s>": 100,
+  "[PAD]": 99
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "facebook/hubert-large-ll60k",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "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,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.0,
+  "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": "hubert",
+  "num_attention_heads": 16,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "pad_token_id": 99,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06c13553a4124d77fc489345c24613fc94ea262191daa5dae9ccee95efc849e
+size 1262224848

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "processor_class": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

runs/Nov04_15-22-41_b924b3f68a42/events.out.tfevents.1699111895.b924b3f68a42.18980.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8a6c0dc3651ac06338ad672245dbf91eea629627b259ab83a71b02150568d0
+size 69789

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "added_tokens_decoder": {
+    "98": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "processor_class": "Wav2Vec2Processor",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b61dec7da213aceb646b5dfc51e1e821b50b994880eb7037a42d5b91a0408ff
+size 4600

vocab.json

@@ -0,0 +1,102 @@
+{
+  "[PAD]": 99,
+  "[UNK]": 98,
+  "a": 1,
+  "b": 2,
+  "c": 3,
+  "d": 4,
+  "e": 5,
+  "f": 6,
+  "g": 7,
+  "h": 8,
+  "i": 9,
+  "j": 10,
+  "k": 11,
+  "l": 12,
+  "m": 13,
+  "n": 14,
+  "o": 15,
+  "p": 16,
+  "q": 17,
+  "r": 18,
+  "s": 19,
+  "t": 20,
+  "u": 21,
+  "v": 22,
+  "w": 23,
+  "x": 24,
+  "y": 25,
+  "z": 26,
+  "|": 0,
+  "ँ": 28,
+  "ं": 29,
+  "ः": 30,
+  "अ": 31,
+  "आ": 32,
+  "इ": 33,
+  "ई": 34,
+  "उ": 35,
+  "ऊ": 36,
+  "ऋ": 37,
+  "ए": 38,
+  "ऐ": 39,
+  "ऑ": 40,
+  "ओ": 41,
+  "औ": 42,
+  "क": 43,
+  "ख": 44,
+  "ग": 45,
+  "घ": 46,
+  "च": 47,
+  "छ": 48,
+  "ज": 49,
+  "झ": 50,
+  "ञ": 51,
+  "ट": 52,
+  "ठ": 53,
+  "ड": 54,
+  "ढ": 55,
+  "ण": 56,
+  "त": 57,
+  "थ": 58,
+  "द": 59,
+  "ध": 60,
+  "न": 61,
+  "प": 62,
+  "फ": 63,
+  "ब": 64,
+  "भ": 65,
+  "म": 66,
+  "य": 67,
+  "र": 68,
+  "ल": 69,
+  "व": 70,
+  "श": 71,
+  "ष": 72,
+  "स": 73,
+  "ह": 74,
+  "़": 75,
+  "ा": 76,
+  "ि": 77,
+  "ी": 78,
+  "ु": 79,
+  "ू": 80,
+  "ृ": 81,
+  "ॅ": 82,
+  "े": 83,
+  "ै": 84,
+  "ॉ": 85,
+  "ो": 86,
+  "ौ": 87,
+  "्": 88,
+  "क़": 89,
+  "ख़": 90,
+  "ग़": 91,
+  "ज़": 92,
+  "ड़": 93,
+  "ढ़": 94,
+  "फ़": 95,
+  "।": 96,
+  "–": 97,
+  "’": 98
+}