Update tiny models for SpeechEncoderDecoderModel-wav2vec2-bert

config.json

@@ -0,0 +1,153 @@
+{
+  "architectures": [
+    "SpeechEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "/tmp/tmp73xden4h/decoder/BertLMHeadModel",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertLMHeadModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 32,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 37,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "bert",
+    "num_attention_heads": 4,
+    "num_hidden_layers": 2,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "return_dict": true,
+    "tie_word_embeddings": true,
+    "type_vocab_size": 16,
+    "use_cache": true,
+    "vocab_size": 30522
+  },
+  "dtype": "float32",
+  "encoder": {
+    "_name_or_path": "/tmp/tmp73xden4h/encoder/Wav2Vec2Model",
+    "activation_dropout": 0.1,
+    "adapter_attn_dim": null,
+    "adapter_kernel_size": 3,
+    "adapter_stride": 2,
+    "add_adapter": false,
+    "apply_spec_augment": true,
+    "architectures": [
+      "Wav2Vec2Model"
+    ],
+    "attention_dropout": 0.1,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "classifier_proj_size": 256,
+    "codevector_dim": 256,
+    "contrastive_logits_temperature": 0.1,
+    "conv_bias": false,
+    "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,
+    "dtype": "float32",
+    "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,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 20,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "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,
+    "model_type": "wav2vec2",
+    "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": 2,
+    "num_negatives": 100,
+    "output_attentions": false,
+    "output_hidden_size": 16,
+    "output_hidden_states": false,
+    "pad_token_id": 0,
+    "problem_type": null,
+    "proj_codevector_dim": 256,
+    "return_dict": true,
+    "tdnn_dilation": [
+      1,
+      2
+    ],
+    "tdnn_dim": [
+      32,
+      32
+    ],
+    "tdnn_kernel": [
+      5,
+      3
+    ],
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32,
+    "xvector_output_dim": 32
+  },
+  "is_encoder_decoder": true,
+  "model_type": "speech-encoder-decoder",
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0"
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 0,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fff34fbf6e0f8e679045cefae3a87cd74651207acce09201d90b751b86fa8ec
+size 4297432

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": false,
+  "sampling_rate": 16000
+}

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

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
+}