Upload model v1

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": 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": "4.5.0.dev0",
+  "vocab_size": 91
+}

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:b099a14c73f1a3195997d3b989c85c6fc8e37da0bdd551d5c4e0f373eb5b5e99
+size 1262306903

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