Add model files

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "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": 91,
+  "transformers_version": "4.4.0",
+  "vocab_size": 92
+}

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 sha256:84cd5e45d5e8ea65d52d2b7251926ae35a6006809274de7e42490270aa887fd1
+size 1262310999

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": "|"}

vocab.json

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