Upload AutomaticSpeechRecognitionPipeline

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 95,
+  "<s>": 94,
+  "[PAD]": 93
+}

config.json

@@ -0,0 +1,82 @@
+{
+  "_name_or_path": "results/georgian/20240903_071718/checkpoint-126710/",
+  "activation_dropout": 0.0,
+  "adapter_act": "relu",
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": true,
+  "apply_spec_augment": false,
+  "architectures": [
+    "Wav2Vec2BertForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 768,
+  "codevector_dim": 768,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_depthwise_kernel_size": 31,
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": true,
+  "diversity_loss_weight": 0.1,
+  "eos_token_id": 2,
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "feature_projection_input_dim": 160,
+  "final_dropout": 0.1,
+  "hidden_act": "swish",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "left_max_position_embeddings": 64,
+  "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": 0.0,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-bert",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 93,
+  "position_embeddings_type": "relative_key",
+  "proj_codevector_dim": 768,
+  "right_max_position_embeddings": 8,
+  "rotary_embedding_base": 10000,
+  "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": "4.44.2",
+  "use_intermediate_ffn_before_adapter": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 96,
+  "xvector_output_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52688c29c5cc6f92ea8d9c959a0d2651a73872f0e3c3024704733bd27c6f604
+size 2423208160

preprocessor_config.json

@@ -0,0 +1,10 @@
+{
+  "feature_extractor_type": "SeamlessM4TFeatureExtractor",
+  "feature_size": 80,
+  "num_mel_bins": 80,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "stride": 2
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,47 @@
+{
+  "added_tokens_decoder": {
+    "92": {
+      "content": "[UNK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "[PAD]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "95": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "replace_word_delimiter_char": " ",
+  "target_lang": null,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "[UNK]",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,96 @@
+{
+  "&": 1,
+  "'": 2,
+  "[PAD]": 93,
+  "[UNK]": 92,
+  "\\": 3,
+  "`": 4,
+  "a": 5,
+  "b": 6,
+  "c": 7,
+  "d": 8,
+  "e": 9,
+  "f": 10,
+  "g": 11,
+  "h": 12,
+  "i": 13,
+  "j": 14,
+  "k": 15,
+  "l": 16,
+  "m": 17,
+  "n": 18,
+  "o": 19,
+  "p": 20,
+  "q": 21,
+  "r": 22,
+  "s": 23,
+  "t": 24,
+  "u": 25,
+  "v": 26,
+  "w": 27,
+  "x": 28,
+  "y": 29,
+  "z": 30,
+  "|": 0,
+  "¬": 32,
+  "´": 33,
+  "á": 34,
+  "ë": 35,
+  "ò": 36,
+  "õ": 37,
+  "ü": 38,
+  "ģ": 39,
+  "ş": 40,
+  "ƣ": 41,
+  "ƶ": 42,
+  "ʙ": 43,
+  "ʻ": 44,
+  "ʼ": 45,
+  "а": 46,
+  "б": 47,
+  "в": 48,
+  "г": 49,
+  "д": 50,
+  "е": 51,
+  "ж": 52,
+  "з": 53,
+  "и": 54,
+  "й": 55,
+  "к": 56,
+  "л": 57,
+  "м": 58,
+  "н": 59,
+  "о": 60,
+  "п": 61,
+  "р": 62,
+  "с": 63,
+  "т": 64,
+  "у": 65,
+  "х": 66,
+  "ч": 67,
+  "ш": 68,
+  "ъ": 69,
+  "ы": 70,
+  "ь": 71,
+  "ю": 72,
+  "ј": 73,
+  "ў": 74,
+  "ғ": 75,
+  "қ": 76,
+  "ҳ": 77,
+  "ӯ": 78,
+  "‒": 79,
+  "–": 80,
+  "—": 81,
+  "―": 82,
+  "‘": 83,
+  "’": 84,
+  "„": 85,
+  "•": 86,
+  "…": 87,
+  "−": 88,
+  "♂": 89,
+  "⚡": 90,
+  "⠀": 91,
+  "️": 92
+}