add model files

config.json

@@ -0,0 +1,76 @@
+{
+  "_name_or_path": "facebook/wav2vec2-large-xlsr-53",
+  "activation_dropout": 0.1,
+  "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": true,
+  "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": "4.5.0.dev0",
+  "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 sha256:287d2888e07d3b6e8650ca7424ac3a26a7e081bf404fc9e267890ab5c3e3ed2d
+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 @@
+{"é": 0, "ơ": 1, "ì": 2, "t": 3, "s": 4, "ờ": 5, "a": 6, "ề": 7, "ệ": 8, "ị": 9, "ấ": 10, "ừ": 11, "y": 12, "e": 13, "ự": 14, "ồ": 15, "ứ": 16, "m": 17, "ằ": 18, "ụ": 19, "ộ": 20, "h": 21, "ẻ": 22, "ẫ": 23, "è": 24, "ọ": 25, "o": 27, "ễ": 28, "ậ": 29, "ặ": 30, "ă": 31, "ỷ": 32, "ợ": 33, "ò": 34, "c": 35, "d": 36, "â": 37, "đ": 38, "õ": 39, "ý": 40, "ẩ": 41, "ữ": 42, "ở": 43, "ạ": 44, "p": 45, "ê": 46, "ẵ": 47, "i": 48, "ớ": 49, "ó": 50, "ể": 51, "ầ": 52, "ô": 53, "ổ": 54, "r": 55, "ẽ": 56, "í": 57, "l": 58, "g": 59, "ả": 60, "ử": 61, "ỉ": 62, "v": 63, "ủ": 64, "u": 65, "ố": 66, "ỵ": 67, "ỹ": 68, "ú": 69, "á": 70, "ỗ": 71, "ỡ": 72, "ù": 73, "n": 74, "ỏ": 75, "b": 76, "ã": 77, "x": 78, "k": 79, "ũ": 80, "ẹ": 81, "ế": 82, "ư": 83, "ĩ": 84, "ỳ": 85, "ắ": 86, "à": 87, "ẳ": 88, "q": 89, "|": 26, "[UNK]": 90, "[PAD]": 91}