cleaning

checkpoints/bigvgan/config.json

@@ -1,63 +0,0 @@
-{
-    "resblock": "1",
-    "num_gpus": 0,
-    "batch_size": 32,
-    "learning_rate": 0.0001,
-    "adam_b1": 0.8,
-    "adam_b2": 0.99,
-    "lr_decay": 0.9999996,
-    "seed": 1234,
-
-    "upsample_rates": [4,4,2,2,2,2],
-    "upsample_kernel_sizes": [8,8,4,4,4,4],
-    "upsample_initial_channel": 1536,
-    "resblock_kernel_sizes": [3,7,11],
-    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
-
-    "use_tanh_at_final": false,
-    "use_bias_at_final": false,
-
-    "activation": "snakebeta",
-    "snake_logscale": true,
-
-    "use_cqtd_instead_of_mrd": true,
-    "cqtd_filters": 128,
-    "cqtd_max_filters": 1024,
-    "cqtd_filters_scale": 1,
-    "cqtd_dilations": [1, 2, 4],
-    "cqtd_hop_lengths": [512, 256, 256],
-    "cqtd_n_octaves": [9, 9, 9],
-    "cqtd_bins_per_octaves": [24, 36, 48],
-
-    "mpd_reshapes": [2, 3, 5, 7, 11],
-    "use_spectral_norm": false,
-    "discriminator_channel_mult": 1,
-    
-    "use_multiscale_melloss": true,
-    "lambda_melloss": 15,
-
-    "clip_grad_norm": 500,
-
-    "segment_size": 65536,
-    "num_mels": 80,
-    "num_freq": 1025,
-    "n_fft": 1024,
-    "hop_size": 256,
-    "win_size": 1024,
-
-    "sampling_rate": 22050,
-
-    "fmin": 0,
-    "fmax": null,
-    "fmax_for_loss": null,
-
-    "normalize_volume": true,
-
-    "num_workers": 4,
-
-    "dist_config": {
-        "dist_backend": "nccl",
-        "dist_url": "tcp://localhost:54321",
-        "world_size": 1
-    }
-}

checkpoints/config.yaml

@@ -1,120 +0,0 @@
-dataset:
-    bpe_model: bpe.model
-    sample_rate: 24000
-    squeeze: false
-    mel:
-        sample_rate: 24000
-        n_fft: 1024
-        hop_length: 256
-        win_length: 1024
-        n_mels: 100
-        mel_fmin: 0
-        normalize: false
-
-gpt:
-    model_dim: 1280
-    max_mel_tokens: 1815
-    max_text_tokens: 600
-    heads: 20
-    use_mel_codes_as_input: true
-    mel_length_compression: 1024
-    layers: 24
-    number_text_tokens: 12000
-    number_mel_codes: 8194
-    start_mel_token: 8192
-    stop_mel_token: 8193
-    start_text_token: 0
-    stop_text_token: 1
-    train_solo_embeddings: false
-    condition_type: "conformer_perceiver"
-    condition_module:
-        output_size: 512
-        linear_units: 2048
-        attention_heads: 8
-        num_blocks: 6
-        input_layer: "conv2d2"
-        perceiver_mult: 2
-    emo_condition_module:
-        output_size: 512
-        linear_units: 1024
-        attention_heads: 4
-        num_blocks: 4
-        input_layer: "conv2d2"
-        perceiver_mult: 2
-
-semantic_codec:
-    codebook_size: 8192
-    hidden_size: 1024
-    codebook_dim: 8
-    vocos_dim: 384
-    vocos_intermediate_dim: 2048
-    vocos_num_layers: 12
-
-s2mel:
-    preprocess_params:
-        sr: 22050
-        spect_params:
-            n_fft: 1024
-            win_length: 1024
-            hop_length: 256
-            n_mels: 80
-            fmin: 0
-            fmax: "None"
-
-    dit_type: "DiT"
-    reg_loss_type: "l1"
-    style_encoder:
-        dim: 192
-    length_regulator:
-        channels: 512
-        is_discrete: false
-        in_channels: 1024
-        content_codebook_size: 2048
-        sampling_ratios: [1, 1, 1, 1]
-        vector_quantize: false
-        n_codebooks: 1
-        quantizer_dropout: 0.0
-        f0_condition: false
-        n_f0_bins: 512
-    DiT:
-        hidden_dim: 512
-        num_heads: 8
-        depth: 13
-        class_dropout_prob: 0.1
-        block_size: 8192
-        in_channels: 80
-        style_condition: true
-        final_layer_type: 'wavenet'
-        target: 'mel'
-        content_dim: 512
-        content_codebook_size: 1024
-        content_type: 'discrete'
-        f0_condition: false
-        n_f0_bins: 512
-        content_codebooks: 1
-        is_causal: false
-        long_skip_connection: true
-        zero_prompt_speech_token: false
-        time_as_token: false
-        style_as_token: false
-        uvit_skip_connection: true
-        add_resblock_in_transformer: false
-    wavenet:
-        hidden_dim: 512
-        num_layers: 8
-        kernel_size: 5
-        dilation_rate: 1
-        p_dropout: 0.2
-        style_condition: true
-
-gpt_checkpoint: gpt.pth
-w2v_stat: wav2vec2bert_stats.pt
-s2mel_checkpoint: s2mel.pth
-emo_matrix: feat2.pt 
-spk_matrix: feat1.pt
-emo_num: [3, 17, 2, 8, 4, 5, 10, 24]
-qwen_emo_path: qwen0.6bemo4-merge/ 
-vocoder:
-    type: "bigvgan"
-    name: "bigvgan"
-version: 2.0