Version 18

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 91, "</s>": 92}

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_V17/wav2vec-large-xlsr-vietnamese-demo",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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,
+  "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,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "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_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "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": 90,
+  "transformers_version": "4.4.0",
+  "vocab_size": 93
+}

preprocessor_config.json

@@ -0,0 +1,8 @@
+{
+  "do_normalize": true,
+  "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:f11e7457f7d31e0e9356d860f44acbbea43e719a816a53ac9bdf5cbb67f1bca7
+size 1262315159

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]"}

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": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_24_1938-0.71+0/wav2vec-large-xlsr-vietnamese-demo/special_tokens_map.json", "tokenizer_file": null, "name_or_path": "/content/gdrive/MyDrive/Colab\\ Notebooks/XLSR_V17/wav2vec-large-xlsr-vietnamese-demo"}

vocab.json

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