Training in progress, step 2000

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 96, "</s>": 97}

config.json

@@ -0,0 +1,120 @@
+{
+  "_name_or_path": "microsoft/wavlm-large",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "WavLMForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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,
+  "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,
+  "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",
+  "max_bucket_distance": 800,
+  "model_type": "wavlm",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_buckets": 320,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_ctc_classes": 80,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 95,
+  "proj_codevector_dim": 768,
+  "replace_prob": 0.5,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 98,
+  "xvector_output_dim": 512
+}

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
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3438c1e59c4b99282ccda476d021bcb0583a0fe8971e918f38dfea9e6aff392
+size 1262404909

runs/Feb21_20-57-50_khanhpluto-Z10PE-D8-WS/1645452144.0730636/events.out.tfevents.1645452144.khanhpluto-Z10PE-D8-WS.20187.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:664e0fa93b3f72950cce62400198d2bb96aaa33c867e07aae754eef0acf6918c
+size 4802

runs/Feb21_20-57-50_khanhpluto-Z10PE-D8-WS/events.out.tfevents.1645452143.khanhpluto-Z10PE-D8-WS.20187.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0ca00de877c1872b01b6341a2ee6554d8503f875197b3bda4a9e192586837a
+size 5257

runs/Feb21_21-17-37_khanhpluto-Z10PE-D8-WS/1645453291.47658/events.out.tfevents.1645453291.khanhpluto-Z10PE-D8-WS.20933.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3be91600aa860620dc97e1a9aa53b602d6e47c79426f781e4a20e55de9de2fa0
+size 4796

runs/Feb21_21-17-37_khanhpluto-Z10PE-D8-WS/events.out.tfevents.1645453291.khanhpluto-Z10PE-D8-WS.20933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7bc29eb03b218d05e4a35d1bac56a0df5da2623740e4a298198d44b02dd884
+size 5726

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": "/home/khanhpluto/.cache/huggingface/transformers/eef53a602abb50f675493980adcc13e5db18ef9d58ca24e362ae6e2bd6a8a3c2.a21d51735cf8667bcd610f057e88548d5d6a381401f6b4501a8bc6c1a9dc8498", "name_or_path": "phongdtd/wavlm-base-plus-vindata", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd6a7dbc62da4ba1bb7373dd2a6dea7fd63f5fb549ae21bf560628ec9b1c109
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"t": 0, "ỵ": 1, "à": 2, "ữ": 3, "ẵ": 4, "ý": 5, "d": 6, "y": 7, "ẽ": 8, "ó": 9, "ỏ": 10, "ọ": 11, "ậ": 12, "ã": 13, "ẫ": 14, "ả": 15, "ư": 16, "ă": 17, "ộ": 18, "ờ": 19, "ẩ": 20, "z": 21, "ầ": 22, "ổ": 23, "è": 24, "n": 25, "ế": 26, "ỹ": 27, "ĩ": 28, "ỗ": 29, "i": 30, "f": 31, "k": 32, "ú": 33, "ẳ": 34, "â": 35, "u": 36, "o": 37, "m": 38, "ử": 39, "ê": 40, "l": 41, "w": 42, "ủ": 43, "ù": 44, "ô": 45, "ề": 46, "đ": 47, "ừ": 48, "á": 49, "ẹ": 50, "ỳ": 51, "ở": 52, "g": 53, "ơ": 54, "ắ": 55, "r": 56, "ể": 57, "q": 58, "p": 59, "x": 60, "e": 61, "a": 62, "ợ": 63, "b": 64, "ằ": 66, "c": 67, "ồ": 68, "ị": 69, "ớ": 70, "s": 71, "ì": 72, "ứ": 73, "h": 74, "í": 75, "é": 76, "ệ": 77, "ỡ": 78, "ạ": 79, "õ": 80, "ỷ": 81, "ẻ": 82, "ặ": 83, "ỉ": 84, "v": 85, "ấ": 86, "ố": 87, "ự": 88, "ễ": 89, "ũ": 90, "ò": 91, "ụ": 92, "j": 93, "|": 65, "[UNK]": 94, "[PAD]": 95}