Files

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 88, "</s>": 89}

alphabet.json

@@ -0,0 +1 @@
+{"labels": [" ", "(", ")", ",", ".", "\u0531", "\u0532", "\u0533", "\u0534", "\u0535", "\u0536", "\u0537", "\u0538", "\u0539", "\u053a", "\u053b", "\u053c", "\u053d", "\u053e", "\u053f", "\u0540", "\u0541", "\u0542", "\u0543", "\u0544", "\u0545", "\u0546", "\u0547", "\u0548", "\u0549", "\u054a", "\u054b", "\u054c", "\u054d", "\u054e", "\u054f", "\u0551", "\u0552", "\u0553", "\u0554", "\u0555", "\u0556", "\u055b", "\u055d", "\u055e", "\u0561", "\u0562", "\u0563", "\u0564", "\u0565", "\u0566", "\u0567", "\u0568", "\u0569", "\u056a", "\u056b", "\u056c", "\u056d", "\u056e", "\u056f", "\u0570", "\u0571", "\u0572", "\u0573", "\u0574", "\u0575", "\u0576", "\u0577", "\u0578", "\u0579", "\u057a", "\u057b", "\u057c", "\u057d", "\u057e", "\u057f", "\u0580", "\u0581", "\u0582", "\u0583", "\u0584", "\u0585", "\u0586", "\u0587", "\u0589", "\u058a", "\u2047", "", "<s>", "</s>"], "is_bpe": false}

config.json

@@ -0,0 +1,108 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-2b",
+  "activation_dropout": 0.0,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 1024,
+  "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": 0.0,
+  "hidden_size": 1920,
+  "initializer_range": 0.02,
+  "intermediate_size": 7680,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "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": 48,
+  "num_negatives": 100,
+  "output_hidden_size": 1920,
+  "pad_token_id": 87,
+  "proj_codevector_dim": 1024,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 90,
+  "xvector_output_dim": 512
+}

language_model/attrs.json

@@ -0,0 +1 @@
+{"alpha": 0.5, "beta": 1.5, "unk_score_offset": -10.0, "score_boundary": true}

language_model/head.cleaned.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c484d5f1c063ea131aae9bf0089e2c37819a1c540962d597a3518a1c2717ea
+size 12846309032

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "Wav2Vec2ProcessorWithLM",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c77a71fd7a47d3c5b4711380f3a4c079cb87da2c3bec60dba23bbc4f62f27842
+size 8638062861

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

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": "|", "replace_word_delimiter_char": " ", "special_tokens_map_file": null, "name_or_path": "20220428-094209--72000", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be70840fd0c7251daa5001e4d0767f2383599e35555bdd510db81a69854d1f92
+size 2991

vocab.json

@@ -0,0 +1 @@
+{"(": 1, ")": 2, ",": 3, ".": 4, "Ա": 5, "Բ": 6, "Գ": 7, "Դ": 8, "Ե": 9, "Զ": 10, "Է": 11, "Ը": 12, "Թ": 13, "Ժ": 14, "Ի": 15, "Լ": 16, "Խ": 17, "Ծ": 18, "Կ": 19, "Հ": 20, "Ձ": 21, "Ղ": 22, "Ճ": 23, "Մ": 24, "Յ": 25, "Ն": 26, "Շ": 27, "Ո": 28, "Չ": 29, "Պ": 30, "Ջ": 31, "Ռ": 32, "Ս": 33, "Վ": 34, "Տ": 35, "Ց": 36, "Ւ": 37, "Փ": 38, "Ք": 39, "Օ": 40, "Ֆ": 41, "՛": 42, "՝": 43, "՞": 44, "ա": 45, "բ": 46, "գ": 47, "դ": 48, "ե": 49, "զ": 50, "է": 51, "ը": 52, "թ": 53, "ժ": 54, "ի": 55, "լ": 56, "խ": 57, "ծ": 58, "կ": 59, "հ": 60, "ձ": 61, "ղ": 62, "ճ": 63, "մ": 64, "յ": 65, "ն": 66, "շ": 67, "ո": 68, "չ": 69, "պ": 70, "ջ": 71, "ռ": 72, "ս": 73, "վ": 74, "տ": 75, "ր": 76, "ց": 77, "ւ": 78, "փ": 79, "ք": 80, "օ": 81, "ֆ": 82, "և": 83, "։": 84, "֊": 85, "|": 0, "[UNK]": 86, "[PAD]": 87}