Initial commit

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": 66,
+  "transformers_version": "4.4.0",
+  "vocab_size": 67
+}

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 sha256:12db76c176937f3d57505a0ef2b7b06ced00a3439796c0e52e9ca1fe1cf3de4a
+size 1262208538

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 @@
+{"ଚ": 0, "ଜ": 1, "।": 2, "ଠ": 3, "ମ": 4, "ସ": 5, "ଵ": 6, "ଙ": 7, "ୋ": 8, "ପ": 9, "ଟ": 10, "ଉ": 11, "ଧ": 12, "ଫ": 13, "–": 14, "ଇ": 15, "ୁ": 16, "ୱ": 17, "ୌ": 18, "'": 19, "଼": 20, "ବ": 21, "୍": 22, "ଓ": 23, "’": 24, "ଂ": 25, "ଞ": 26, "ନ": 27, "ଝ": 28, "ି": 29, "ା": 30, "ଡ": 32, "ଘ": 33, "ତ": 34, "|": 35, "ଖ": 36, "େ": 37, "ଛ": 38, "ଲ": 39, "ଣ": 40, "ୀ": 41, "ଁ": 42, "କ": 43, "ୈ": 44, "ୃ": 45, "ର": 46, "ଷ": 47, "ଳ": 48, "ଅ": 49, "ଭ": 50, "ଯ": 51, "ଶ": 52, "ଢ": 53, "ଃ": 54, "ୂ": 55, "ଦ": 56, "ୟ": 57, "ହ": 58, "ଆ": 59, "ଊ": 60, "ଥ": 61, "ଏ": 62, "ଗ": 63, "ଈ": 64, "/": 31, "[UNK]": 65, "[PAD]": 66}