upload model files

config.json

@@ -0,0 +1,298 @@
+{
+  "architectures": [
+    "SpeechEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "facebook/bart-base",
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": true,
+    "add_final_layer_norm": false,
+    "architectures": [
+      "BartModel"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 768,
+    "decoder_attention_heads": 12,
+    "decoder_ffn_dim": 3072,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 6,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": true,
+    "encoder_attention_heads": 12,
+    "encoder_ffn_dim": 3072,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 6,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": 0,
+    "forced_eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 3,
+    "normalize_before": false,
+    "normalize_embedding": true,
+    "num_beam_groups": 1,
+    "num_beams": 4,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "length_penalty": 1.0,
+        "max_length": 128,
+        "min_length": 12,
+        "num_beams": 4
+      },
+      "summarization_cnn": {
+        "length_penalty": 2.0,
+        "max_length": 142,
+        "min_length": 56,
+        "num_beams": 4
+      },
+      "summarization_xsum": {
+        "length_penalty": 1.0,
+        "max_length": 62,
+        "min_length": 11,
+        "num_beams": 6
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "facebook/wav2vec2-base",
+    "activation_dropout": 0.0,
+    "adapter_attn_dim": null,
+    "adapter_kernel_size": 3,
+    "adapter_stride": 2,
+    "add_adapter": true,
+    "add_cross_attention": false,
+    "apply_spec_augment": true,
+    "architectures": [
+      "Wav2Vec2ForPreTraining"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "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": [
+      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
+    ],
+    "cross_attention_hidden_size": null,
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "decoder_start_token_id": null,
+    "diversity_loss_weight": 0.1,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "do_stable_layer_norm": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "feat_extract_activation": "gelu",
+    "feat_extract_norm": "group",
+    "feat_proj_dropout": 0.0,
+    "feat_quantizer_dropout": 0.0,
+    "final_dropout": 0.0,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "freeze_feat_extract_train": true,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "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_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_min_space": 1,
+    "mask_time_other": 0.0,
+    "mask_time_prob": 0.05,
+    "mask_time_selection": "static",
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "wav2vec2",
+    "no_mask_channel_overlap": false,
+    "no_mask_time_overlap": false,
+    "no_repeat_ngram_size": 0,
+    "num_adapter_layers": 3,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "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": 12,
+    "num_negatives": 100,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_size": 768,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "proj_codevector_dim": 256,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "tdnn_dilation": [
+      1,
+      2,
+      3,
+      1,
+      1
+    ],
+    "tdnn_dim": [
+      512,
+      512,
+      512,
+      512,
+      1500
+    ],
+    "tdnn_kernel": [
+      5,
+      3,
+      3,
+      1,
+      1
+    ],
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32,
+    "xvector_output_dim": 512
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "max_length": 200,
+  "model_type": "speech-encoder-decoder",
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0"
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2d008bd3696d6ef1d006132fd9332378ab94817bbb300badfb351ccd193fa7
+size 804433536

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

run.py

@@ -0,0 +1,19 @@
+from transformers import SpeechEncoderDecoderModel, AutoFeatureExtractor, AutoTokenizer, Wav2Vec2Processor
+
+# checkpoints to leverage
+encoder_id = "facebook/wav2vec2-base"
+decoder_id = "facebook/bart-base"
+
+# load and save speech-encoder-decoder model
+# set some hyper-parameters for training and evaluation
+model = SpeechEncoderDecoderModel.from_encoder_decoder_pretrained(encoder_id, decoder_id, encoder_add_adapter=True, encoder_feat_proj_dropout=0.0, encoder_layerdrop=0.0, max_length=200, num_beams=5)
+model.config.decoder_start_token_id = model.decoder.config.bos_token_id
+model.config.pad_token_id = model.decoder.config.pad_token_id
+model.config.eos_token_id = model.decoder.config.eos_token_id
+model.save_pretrained("./")
+
+# load and save processor
+feature_extractor = AutoFeatureExtractor.from_pretrained(encoder_id)
+tokenizer = AutoTokenizer.from_pretrained(decoder_id)
+processor = Wav2Vec2Processor(feature_extractor, tokenizer)
+processor.save_pretrained("./")

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "processor_class": "Wav2Vec2Processor",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}