Upload tiny models for Wav2Vec2ConformerForXVector

config.json

@@ -0,0 +1,91 @@
+{
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ConformerForXVector"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "conformer_conv_dropout": 0.1,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_depthwise_kernel_size": 31,
+  "conv_dim": [
+    32,
+    32,
+    32
+  ],
+  "conv_kernel": [
+    8,
+    8,
+    8
+  ],
+  "conv_stride": [
+    4,
+    4,
+    4
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 20,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 2,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.5,
+  "max_source_positions": 5000,
+  "model_type": "wav2vec2-conformer",
+  "num_adapter_layers": 1,
+  "num_attention_heads": 2,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 2,
+  "num_conv_pos_embeddings": 16,
+  "num_feat_extract_layers": 3,
+  "num_hidden_layers": 4,
+  "num_negatives": 100,
+  "output_hidden_size": 16,
+  "pad_token_id": 0,
+  "position_embeddings_type": "relative",
+  "proj_codevector_dim": 256,
+  "rotary_embedding_base": 10000,
+  "tdnn_dilation": [
+    1,
+    2
+  ],
+  "tdnn_dim": [
+    32,
+    32
+  ],
+  "tdnn_kernel": [
+    5,
+    3
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 32
+}

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": "Wav2Vec2Processor",
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74e4f335aedde64406dd863ab3e661ac752c495c64cbc8de929369060786fae
+size 251589

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "do_normalize": true,
+  "eos_token": "</s>",
+  "model_max_length": 9223372036854775807,
+  "pad_token": "<pad>",
+  "replace_word_delimiter_char": " ",
+  "return_attention_mask": false,
+  "special_tokens_map_file": "/home/runner/.cache/huggingface/hub/models--facebook--wav2vec2-base-960h/snapshots/22aad52d435eb6dbaf354bdad9b0da84ce7d6156/special_tokens_map.json",
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "unk_token": "<unk>",
+  "word_delimiter_token": "|"
+}

vocab.json

@@ -0,0 +1,34 @@
+{
+  "'": 27,
+  "</s>": 2,
+  "<pad>": 0,
+  "<s>": 1,
+  "<unk>": 3,
+  "A": 7,
+  "B": 24,
+  "C": 19,
+  "D": 14,
+  "E": 5,
+  "F": 20,
+  "G": 21,
+  "H": 11,
+  "I": 10,
+  "J": 29,
+  "K": 26,
+  "L": 15,
+  "M": 17,
+  "N": 9,
+  "O": 8,
+  "P": 23,
+  "Q": 30,
+  "R": 13,
+  "S": 12,
+  "T": 6,
+  "U": 16,
+  "V": 25,
+  "W": 18,
+  "X": 28,
+  "Y": 22,
+  "Z": 31,
+  "|": 4
+}