Delete pretrained-models

pretrained-models/config.yaml

@@ -1,129 +0,0 @@
-__set_seed1: !apply:random.seed [1986]
-__set_seed2: !apply:numpy.random.seed [1986]
-__set_seed3: !apply:torch.manual_seed [1986]
-__set_seed4: !apply:torch.cuda.manual_seed_all [1986]
-
-sample_rate: 22050
-text_encoder_input_size: 512
-llm_input_size: 1024
-llm_output_size: 1024
-spk_embed_dim: 192
-
-llm: !new:src.llm.llm.TransformerLM
-    text_encoder_input_size: !ref <text_encoder_input_size>
-    llm_input_size: !ref <llm_input_size>
-    llm_output_size: !ref <llm_output_size>
-    text_token_size: 60515
-    speech_token_size: 4096
-    length_normalized_loss: True
-    lsm_weight: 0
-    spk_embed_dim: !ref <spk_embed_dim>
-    text_encoder: !new:src.transformer.encoder.ConformerEncoder
-        input_size: !ref <text_encoder_input_size>
-        output_size: 1024
-        attention_heads: 16
-        linear_units: 4096
-        num_blocks: 6
-        dropout_rate: 0.1
-        positional_dropout_rate: 0.1
-        attention_dropout_rate: 0.0
-        normalize_before: True
-        input_layer: 'linear'
-        pos_enc_layer_type: 'rel_pos_espnet'
-        selfattention_layer_type: 'rel_selfattn'
-        use_cnn_module: False
-        macaron_style: False
-        use_dynamic_chunk: False
-        use_dynamic_left_chunk: False
-        static_chunk_size: 1
-    llm: !new:src.transformer.encoder.TransformerEncoder
-        input_size: !ref <llm_input_size>
-        output_size: !ref <llm_output_size>
-        attention_heads: 16
-        linear_units: 4096
-        num_blocks: 14
-        dropout_rate: 0.1
-        positional_dropout_rate: 0.1
-        attention_dropout_rate: 0.0
-        input_layer: 'linear_legacy'
-        pos_enc_layer_type: 'rel_pos_espnet'
-        selfattention_layer_type: 'rel_selfattn'
-        static_chunk_size: 1
-    sampling: !name:src.utils.common.ras_sampling
-        top_p: 0.8
-        top_k: 25
-        win_size: 10
-        tau_r: 0.1
-
-flow: !new:src.flow.flow.MaskedDiffWithXvec
-    input_size: 512
-    output_size: 80
-    spk_embed_dim: !ref <spk_embed_dim>
-    output_type: 'mel'
-    vocab_size: 4096
-    input_frame_rate: 25
-    only_mask_loss: True
-    encoder: !new:src.transformer.encoder.ConformerEncoder
-        output_size: 512
-        attention_heads: 8
-        linear_units: 2048
-        num_blocks: 6
-        dropout_rate: 0.1
-        positional_dropout_rate: 0.1
-        attention_dropout_rate: 0.1
-        normalize_before: True
-        input_layer: 'linear'
-        pos_enc_layer_type: 'rel_pos_espnet'
-        selfattention_layer_type: 'rel_selfattn'
-        input_size: 512
-        use_cnn_module: False
-        macaron_style: False
-    length_regulator: !new:src.flow.length_regulator.InterpolateRegulator
-        channels: 80
-        sampling_ratios: [1, 1, 1, 1]
-    decoder: !new:src.flow.flow_matching.ConditionalCFM
-        in_channels: 240
-        n_spks: 1
-        spk_emb_dim: 80
-        cfm_params: !new:omegaconf.DictConfig
-            content:
-                sigma_min: 1e-06
-                solver: 'euler'
-                t_scheduler: 'cosine'
-                training_cfg_rate: 0.2
-                inference_cfg_rate: 0.7
-                reg_loss_type: 'l1'
-        estimator: !new:src.flow.decoder.ConditionalDecoder
-            in_channels: 320
-            out_channels: 80
-            channels: [256, 256]
-            dropout: 0.0
-            attention_head_dim: 64
-            n_blocks: 4
-            num_mid_blocks: 12
-            num_heads: 8
-            act_fn: 'gelu'
-
-hift:
-    in_channels: 80
-    base_channels: 512
-    nb_harmonics: 8
-    sampling_rate: !ref <sample_rate>
-    nsf_alpha: 0.1
-    nsf_sigma: 0.003
-    nsf_voiced_threshold: 10
-    upsample_rates: [8, 8]
-    upsample_kernel_sizes: [16, 16]
-    istft_params:
-        n_fft: 16
-        hop_len: 4
-    resblock_kernel_sizes: [3, 7, 11]
-    resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
-    source_resblock_kernel_sizes: [7, 11]
-    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5]]
-    lrelu_slope: 0.1
-    audio_limit: 0.99
-    f0_predictor: !new:src.hifigan.f0_predictor.ConvRNNF0Predictor
-        num_class: 1
-        in_channels: 80
-        cond_channels: 512

pretrained-models/flow.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1411de192039a21d53f0bf1968feb50586ce71d81ea1443f8163f4d1c46c5455
-size 419901370

pretrained-models/hift.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:91e679b6ca1eff71187ffb4f3ab0444935594cdcc20a9bd12afad111ef8d6012
-size 81896716

pretrained-models/llm.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c1773e5afe16a88ee82e33cf510a07717ce1346d2e74856733d72dc297a9a017
-size 1260740644

pretrained-models/speech_embedding.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6ac6a63997761ae2997373e2ee1c47040854b4b759ea41ec48e4e42df0f4d73
-size 28303423

pretrained-models/speech_tokenizer.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:56285ddd4a83e883ee0cb9f8d69c1089b53a94b1f78ff7e4a0224a27eb4cb486
-size 522625011