add final models

config.json

@@ -0,0 +1,87 @@
+{
+  "_name_or_path": ".",
+  "activation_dropout": 0.0,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "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,
+  "diversity_loss_weight": 0.1,
+  "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,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "gradient_checkpointing": false,
+  "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_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": 24,
+  "num_negatives": 100,
+  "pad_token_id": 91,
+  "proj_codevector_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 92
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "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 sha256:989f6c8eab6e7924866056dd6bf0db89ec55342bd9b2b66708865400082fbbcf
+size 1262294961

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 @@
+{"r": 0, "ɪ": 1, "ɖ": 2, "é": 3, "ɴ": 4, "ʔ": 5, "ɒ": 6, "l": 7, "θ": 8, "ɨ": 9, "ʑ": 10, "ϊ": 11, "ä": 12, "e": 13, "ɱ": 14, "a": 15, "ɔ": 16, "#": 17, "t͡s": 18, "g": 19, "ː": 20, "̥": 21, "ϋ": 22, "ʕ": 23, "ç": 24, "w": 25, "ΐ": 26, "̇": 27, "h": 28, "ɡ": 29, "d": 30, "ʒ": 31, "t": 32, "d͡ʑ": 33, "ʎ": 34, "ɳ": 35, "ɦ": 36, "̪": 37, "ˤ": 38, "u": 39, "z": 40, "ɕ": 41, "ɲ": 42, "ɛ": 43, " ": 44, "ʝ": 45, "v": 46, "y": 47, "n": 48, "ŋ": 49, "ɯ": 50, "x": 51, "ʐ": 52, "ɭ": 53, "æ": 54, "ɾ": 55, "ɸ": 56, "t͡ʂ": 57, "ɑ": 58, "b": 59, "c": 60, "ɣ": 61, "f": 62, "d͡z": 63, "ʃ": 64, "ʋ": 65, "'": 66, "ð": 67, "j": 68, "ħ": 69, "̞": 70, "d͡ʐ": 71, "q": 72, "m": 73, "t͡ɕ": 74, "i": 75, "s": 76, "á": 77, "ø": 78, "ஃ": 79, "k": 80, "ɐ": 81, "p": 82, "ʲ": 83, "̃": 84, "o": 85, "ʂ": 86, "ɻ": 87, "ɟ": 88, "ʈ": 89, "[UNK]": 90, "[PAD]": 91}