Upload folder using huggingface_hub

CosyVoice-300M-25Hz/FLOW_VERSION

@@ -0,0 +1 @@
+c2f46df20d1c18f51b9cda8b4f812427  flow.pt

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 +1,64 @@
+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.bigvgan.bigvgan.BigVGAN
+    use_cuda_kernel: false
+    num_mels: !ref <mel_conf[num_mels]>
+    upsample_initial_channel: 768
+    upsample_rates: [5, 4, 3, 2, 2, 2]
+    upsample_kernel_sizes: [11, 8, 7, 4, 4, 4]
+    resblock: "1"
+    resblock_kernel_sizes: [3,7,11]
+    resblock_dilation_sizes: [[1,3,5], [1,3,5], [1,3,5]]
+
+    activation: "snakebeta"
+    snake_logscale: true
+
+    use_tanh_at_final: false
+    use_bias_at_final: false

CosyVoice-300M-25Hz/flow.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ed68d0cf1bc13c86da5cb73241da37e8d7cebdfd13b92a620c6b3cb3aab872b
+size 615274252

CosyVoice-300M-25Hz/hift.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bb4b495742ab00d92fd5ccb8d576164425d3a7d43a7f894ab0370d64e8a190
+size 117228443

CosyVoice-300M-25Hz/speech_tokenizer_v1.onnx

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