Upload folder using huggingface_hub

CosyVoice-300M-25Hz/FLOW_VERSION

@@ -0,0 +1,2 @@
+/mnt/wby-jfs/models/train/flow_matching/flow_v2_1node_vq0206_dit_v8_fullattn_exp0227_sft_exp0408_stepaudio_sft_exp0616/model_epoch_5_whole.pt
+fae53942e60310eb172b170396202069

CosyVoice-300M-25Hz/campplus.onnx

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

CosyVoice-300M-25Hz/cosyvoice.yaml

@@ -0,0 +1,72 @@
+mel_conf:
+    num_mels: 80
+    n_fft: 1920
+    hop_size: 480
+    win_size: 1920
+    sampling_rate: 24000
+    fmin: 0
+    fmax: 8000
+    
+
+flow: !new:stepvocoder.cosyvoice2.flow.flow.CausalMaskedDiffWithXvec
+    input_size: 512
+    output_size: 80
+    spk_embed_dim: 192
+    output_type: 'mel'
+    vocab_size: 5121    # 1024(vq02) + 4096(vq06) + 1(vq02-pad)
+    input_embedding: !new:stepvocoder.cosyvoice2.embedding.dual_codebook.DualCodebookEmbedding
+      vocab_size: 5121  # 1024(vq02) + 4096(vq06) + 1(vq02-pad)
+      input_size: 512
+    encoder: !new:stepvocoder.cosyvoice2.transformer.upsample_encoder_v2.UpsampleConformerEncoderV2
+        input_size: 512
+        output_size: 512
+        input_layer: 'linear'
+        pre_lookahead_len: 3
+        num_blocks: 6
+        num_up_blocks: 4
+        up_stride: 2
+        up_scale_factor: 2
+        attention_heads: 8
+        pos_enc_layer_type: 'rel_pos_espnet'
+        selfattention_layer_type: 'rel_selfattn'
+        key_bias: true
+        linear_units: 2048
+        dropout_rate: 0.1
+        positional_dropout_rate: 0.1
+        attention_dropout_rate: 0.1
+        normalize_before: True
+    decoder: !new:stepvocoder.cosyvoice2.flow.flow_matching.CausalConditionalCFM
+        inference_cfg_rate: 0.7
+        estimator: !new:stepvocoder.cosyvoice2.flow.decoder_dit.DiT
+            in_channels: 320
+            out_channels: 80
+            mlp_ratio: 4.0
+            depth: 16
+            num_heads: 8
+            head_dim: 64
+            hidden_size: 512
+
+
+hift: !new:stepvocoder.cosyvoice2.hifigan.generator.HiFTGenerator
+    in_channels: 80
+    base_channels: 512
+    nb_harmonics: 8
+    sampling_rate: 24000
+    nsf_alpha: 0.1
+    nsf_sigma: 0.003
+    nsf_voiced_threshold: 10
+    upsample_rates: [8, 5, 3]
+    upsample_kernel_sizes: [16, 11, 7]
+    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, 7, 11]
+    source_resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
+    lrelu_slope: 0.1
+    audio_limit: 0.99
+    f0_predictor: !new:stepvocoder.cosyvoice2.hifigan.f0_predictor.ConvRNNF0Predictor
+        num_class: 1
+        in_channels: 80
+        cond_channels: 512

CosyVoice-300M-25Hz/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f18fcb9c374bb8d8ae229e2f7618b6effaa208609bd0407fc661234125531c
+size 615269316

CosyVoice-300M-25Hz/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3386cc880324d4e98e05987b99107f49e40ed925b8ecc87c1f4939432d429879
+size 83390254

CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx

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