First version of the wav2vec2-large-xlsr-kn model and tokenizer.

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": 100,
+  "transformers_version": "4.5.0.dev0",
+  "vocab_size": 101
+}

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 sha256:56255e6468e3ae12ca97a0573c5170a70b9e73cc96699ba5e9da4cd480b59557
+size 1262347927

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": "|"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afc7187af982f2cc7b7f9be7bdf85ffd484276fc48bdea7c481020731cd7a468
+size 2287

vocab.json

@@ -0,0 +1 @@
+{"6": 0, "೨": 1, "ೇ": 2, "ಛ": 3, "ಿ": 4, "ಞ": 5, "ಊ": 6, "೧": 7, "ಾ": 8, "n": 9, "'": 10, "ಆ": 11, "೯": 12, "/": 13, "2": 14, "ಉ": 15, "ಂ": 16, "8": 17, "ಢ": 18, "೪": 19, "೮": 20, "ಲ": 21, "ೌ": 22, "ಙ": 23, "ವ": 24, "ಬ": 25, "ಧ": 26, "ಗ": 27, "ೋ": 28, "ಳ": 29, "e": 30, "u": 31, "ಥ": 32, "ಭ": 33, "ಚ": 34, "೩": 35, "ಖ": 36, "’": 37, "ಓ": 38, "ಠ": 39, "ಈ": 40, "ಕ": 41, "ಔ": 42, "ು": 43, "ಋ": 45, "ತ": 46, "ಐ": 47, "ೀ": 48, "ೆ": 49, "ಮ": 50, "ಘ": 51, "೫": 52, "ೃ": 53, "‌": 54, "ೈ": 55, "೬": 56, "5": 57, "ಷ": 58, "t": 59, "1": 60, "‍": 61, "_": 62, "ಏ": 63, "r": 64, "ದ": 65, "ರ": 66, "x": 67, "ಇ": 68, "್": 69, "7": 70, "೭": 71, "(": 72, "ಫ": 73, "ನ": 74, "ೊ": 75, "ೂ": 76, "ಅ": 77, "ಪ": 78, "ಝ": 79, ")": 80, "ಜ": 81, "ಒ": 82, "ಯ": 83, "೦": 84, "3": 85, "4": 86, "l": 87, "ಶ": 88, "ಣ": 89, "ಟ": 90, "ಎ": 91, "ಸ": 92, "ಹ": 93, "ಃ": 94, "0": 95, "i": 96, "9": 97, "ಡ": 98, "|": 44, "[UNK]": 99, "[PAD]": 100}