diff --git a/config.json b/config.json new file mode 100644 index 0000000..fa661fa --- /dev/null +++ b/config.json @@ -0,0 +1,100 @@ +{ + "_name_or_path": "hf-internal-testing/tiny-random-wav2vec2", + "activation_dropout": 0.1, + "adapter_kernel_size": 3, + "adapter_stride": 2, + "add_adapter": false, + "apply_spec_augment": true, + "architectures": [ + "WavLMForSequenceClassification" + ], + "attention_dropout": 0.1, + "bos_token_id": 1, + "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": true, + "eos_token_id": 2, + "feat_extract_activation": "gelu", + "feat_extract_dropout": 0.0, + "feat_extract_norm": "layer", + "feat_proj_dropout": 0.1, + "feat_quantizer_dropout": 0.0, + "final_dropout": 0.1, + "gradient_checkpointing": false, + "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": 10, + "mask_time_min_masks": 2, + "mask_time_prob": 0.05, + "max_bucket_distance": 800, + "model_type": "wavlm", + "num_adapter_layers": 3, + "num_attention_heads": 2, + "num_buckets": 320, + "num_codevector_groups": 2, + "num_codevectors_per_group": 320, + "num_conv_pos_embedding_groups": 2, + "num_conv_pos_embeddings": 16, + "num_ctc_classes": 80, + "num_feat_extract_layers": 3, + "num_hidden_layers": 4, + "num_negatives": 10, + "output_hidden_size": 16, + "pad_token_id": 0, + "proj_codevector_dim": 256, + "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": "4.16.0.dev0", + "use_weighted_layer_sum": false, + "vocab_size": 32, + "xvector_output_dim": 512 +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..a0b7227 --- /dev/null +++ b/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 +} diff --git a/pytorch_model.bin b/pytorch_model.bin new file mode 100644 index 0000000..771718e --- /dev/null +++ b/pytorch_model.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3011a742dd6656a66ddb868241e5de03e0eb651a18e7d30f7eab4507ab3597cc +size 167161