Add model

config.json

@@ -0,0 +1,81 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token": "<s>",
+  "bos_token_id": 0,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "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": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_lower_case": false,
+  "do_stable_layer_norm": false,
+  "eos_token": "</s>",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "pad_token": "[PAD]",
+  "pad_token_id": 1,
+  "proj_codevector_dim": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.1",
+  "unk_token": "[UNK]",
+  "vocab_size": 65,
+  "word_delimiter_token": "|"
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52865d3158e86c846ba54e965a0a024e73fc1e6d44d859ae06c24b560f23f972
+size 377768535

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": "|", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

vocab.json

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