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": 83,
+  "transformers_version": "4.4.0",
+  "vocab_size": 84
+}

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:b3ccb380e94316fc1dfd54cf97f15e373fb1160540a71b0fd5e727357b34fde5
+size 1262278231

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 @@
+{"ば": 0, "べ": 1, "た": 2, "か": 3, "を": 4, "あ": 5, "に": 6, "ど": 7, "ち": 8, "っ": 9, "ね": 10, "お": 11, "ぐ": 12, "ぉ": 13, "ひ": 14, "ず": 15, "ぞ": 16, "だ": 17, "ぃ": 18, "ざ": 19, "え": 20, "め": 21, "ぷ": 22, "ぼ": 23, "け": 24, "と": 25, "ぇ": 26, "こ": 27, "づ": 28, "が": 29, "よ": 30, "ぢ": 31, "し": 32, "く": 33, "せ": 34, "な": 35, "ー": 36, "わ": 37, "ま": 38, "ご": 39, "ほ": 40, "で": 41, "つ": 42, "ゃ": 43, "ぱ": 44, "び": 45, "ゆ": 46, "む": 48, "へ": 49, "い": 50, "ろ": 51, "れ": 52, "ぜ": 53, "さ": 54, "う": 55, "み": 56, "や": 57, "げ": 58, "き": 59, "の": 60, "ゔ": 61, "ょ": 62, "ゅ": 63, "り": 64, "ぴ": 65, "ぁ": 66, "ら": 67, "ふ": 68, "ん": 69, "す": 70, "る": 71, "ぽ": 72, "ぬ": 73, "ぶ": 74, "そ": 75, "も": 76, "は": 77, "じ": 78, "ぎ": 79, "ぺ": 80, "て": 81, "|": 47, "[UNK]": 82, "[PAD]": 83}