Duplicate from IAHispano/Applio

Co-authored-by: Blaise <blaise-tk@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,47 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+Resources/ffmpeg.exe filter=lfs diff=lfs merge=lfs -text
+Resources/ffprobe.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.0.9.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.1.0.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.1.1.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.5.0.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.2.0.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.2.1.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.2.2.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.2.3.exe filter=lfs diff=lfs merge=lfs -text
+Compiled/ApplioV3.2.4.exe filter=lfs diff=lfs merge=lfs -text
+Resources/formant/stftpitchshift filter=lfs diff=lfs merge=lfs -text

Compiled/Linux/ApplioV3.2.8-bugfix.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f27ddea9bc182cbac1b2d809f329840ccc6bc1391b8b4918932fbbc396903d21
+size 7544065874

Compiled/Linux/ApplioV3.2.9.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c4785a1c1d6c26ed01061b70e14f6cdba6d00646fffb2aed7b6ef5b10d07d59
+size 7573040499

Compiled/Linux/ApplioV3.3.0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a10298f10f85e8c49fa8d7490053fde5af3ce76446eb4d812cdfd3db9715c71
+size 9575763753

Compiled/Windows/ApplioV3.2.8-bugfix.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c68274095cc9d11930dd4a783acea7a9de641753ea1033431fbb07a88ef74b
+size 4220255228

Compiled/Windows/ApplioV3.2.9.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87e6329870f36a31106913a627a1602a1abd84085884d875f83bd53f05b82941
+size 4236244130

Compiled/Windows/ApplioV3.3.0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:641bddfded4e21b735397572420b34d09d1905c72939a9d629ce981f5fc68ea2
+size 4873873650

Compiled/Windows/ApplioV3.3.1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af3742262e0ea6724eeca188ad95f9910eccd658321ee2f8f2a88b51df6b4f50
+size 4879206120

Compiled/Windows/ApplioV3.4.0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:071fb5ec31e12c7afc90aa3a8b1af4842840b44a7b14ccb2fd2b60e9e5268344
+size 4879293026

Compiled/Windows/ApplioV3.5.0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbe741466989905890d1e046909a6f8d26feaa0244c5defb43e8e116cf4cb6df
+size 4899282098

Compiled/Windows/ApplioV3.5.1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8ac88f58aeb265e8a6651085479106410c3602cbe3f64918bc63f64ad768ec
+size 4862979406

Compiled/Windows/ApplioV3.6.0.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6dc30842d9dd28d330ad3a07afd052110e67cb8901c820bb0e5181054b5d79a2
+size 5169475119

Compiled/Windows/ApplioV3.6.1.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c4f3a2eb8b0de1be5f1bf0d34f7437855eaf339c68ee7697d408c8e9cba6fc1
+size 5475095742

Compiled/Windows/ApplioV3.6.2.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0763606b8e0b2e2b75077eac5af2772a1682166a812acd9475622fe4c6fb1df9
+size 5440885048

Enviroment/Colab/Pnpur.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edc00278eee827bf24237492b2a91ccdafdb98393a41ec9b4fff9d9a62b5abe6
+size 2529458747

Enviroment/Colab/Pnpur_.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa42df46fbb0f7e9fad7d493a0ed317754920703be9d148122d766b4aef48ccf
+size 3036863135

Enviroment/Colab/tmp_packages.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6859c5c7f37bb664926db714bf68a9c2b909f03fa84644cddb1fa3b51a8682
+size 30779249

Enviroment/Kaggle/Kaggle.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221e9e89d15775a71f2458b30dee22c409f01e0ca9a9463fea43234c7dabc784
+size 2909878809

Enviroment/Kaggle/KaggleV2.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1c19a66ca46bf47f56dd6e46633069b51997d7acd295e36c2e82dd87adc45d8
+size 3249845631

Enviroment/Kaggle/bin_kaggle.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e273205da615c7ebda701125fbfe08a701fa26d0658e958001c51c69197644
+size 10203128

README.md

@@ -0,0 +1,100 @@
+---
+pipeline_tag: audio-to-audio
+tags:
+- AI
+- RVC
+- VITS
+- VC
+- Voice Conversion
+- Voice2Voice
+license: mit
+datasets:
+- CSTR-Edinburgh/vctk
+base_model:
+- lj1995/VoiceConversionWebUI
+---
+
+<h1 align="center">
+  <a href="https://applio.org" target="_blank"><img src="https://github.com/IAHispano/Applio/assets/133521603/78e975d8-b07f-47ba-ab23-5a31592f322a" alt="Applio"></a>
+</h1>
+
+<p align="center">A simple, high-quality voice conversion tool, focused on ease of use and performance.</p>
+
+<p align="center">
+  <a href="https://applio.org" target="_blank">🌐 Website</a>
+  •
+  <a href="https://docs.applio.org" target="_blank">📚 Documentation</a>
+  •
+  <a href="https://discord.gg/urxFjYmYYh" target="_blank">☎️ Discord</a>
+</p>
+
+<p align="center">
+  <a href="https://github.com/IAHispano/Applio-Plugins" target="_blank">🛒 Plugins</a>
+  •
+  <a href="https://huggingface.co/IAHispano/Applio/tree/main/Compiled" target="_blank">📦 Compiled</a>
+  •
+  <a href="https://applio.org/playground" target="_blank">🎮 Playground</a>
+  •
+  <a href="https://colab.research.google.com/github/iahispano/applio/blob/master/assets/Applio.ipynb" target="_blank">🔎 Google Colab (UI)</a>
+  •
+  <a href="https://colab.research.google.com/github/iahispano/applio/blob/master/assets/Applio_NoUI.ipynb" target="_blank">🔎 Google Colab (No UI)</a>
+</p>
+
+## Introduction
+
+Applio is a powerful voice conversion tool focused on simplicity, quality, and performance. Whether you're an artist, developer, or researcher, Applio offers a straightforward platform for high-quality voice transformations. Its flexible design allows for customization through plugins and configurations, catering to a wide range of projects.
+
+## Terms of Use
+The use of Applio is entirely at your own discretion and responsibility. By using this tool, you agree to:
+
+1. Respect all applicable copyrights, intellectual property rights, and privacy rights. Ensure that any audio or material processed through Applio is either owned by you or used with explicit permission from the rightful owner.
+
+2. Avoid using Applio in ways that may harm, defame, or infringe upon the rights of others. This includes, but is not limited to, the creation or distribution of unauthorized content.
+
+3. Comply with all relevant laws and regulations governing the use of AI and voice transformation tools in your jurisdiction.
+
+Applio and its contributors are not liable for any misuse of the tool. The responsibility for adhering to ethical practices and legal compliance lies solely with the user. Applio does not endorse or support any activities that result in harm to individuals, groups, or entities. All official models distributed by Applio have been trained under public use datasets such as VCTK.
+
+## Getting Started
+
+### 1. Installation
+
+Run the installation script based on your operating system:
+
+- **Windows:** Double-click `run-install.bat`.
+- **Linux/macOS:** Execute `run-install.sh`.
+
+### 2. Running Applio
+
+Start Applio using:
+
+- **Windows:** Double-click `run-applio.bat`.
+- **Linux/macOS:** Run `run-applio.sh`.
+
+This launches the Gradio interface in your default browser.
+
+### 3. Optional: TensorBoard Monitoring
+
+To monitor training or visualize data:
+
+- **Windows:** Run `run-tensorboard.bat`.
+- **Linux/macOS:** Run `run-tensorboard.sh`.
+
+For more detailed instructions, visit the [documentation](https://docs.applio.org).
+
+## Commercial Usage
+
+For commercial use, follow the [MIT license](./LICENSE) and contact us at support@applio.org to ensure ethical use. The use of Applio-generated audio files must comply with applicable copyrights. Consider supporting Applio’s development [through a donation](https://ko-fi.com/iahispano).
+
+## References
+
+Applio is made possible thanks to these projects and their references:
+
+- [gradio-screen-recorder](https://huggingface.co/spaces/gstaff/gradio-screen-recorder) by gstaff
+- [rvc-cli](https://github.com/blaisewf/rvc-cli) by blaisewf
+
+### Contributors
+
+<a href="https://github.com/IAHispano/Applio/graphs/contributors" target="_blank">
+  <img src="https://contrib.rocks/image?repo=IAHispano/Applio" />
+</a>

Resources/contentvec_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
+size 189507909

Resources/embedders/chinese_hubert_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cd5db6302ae2e79b5972cd02ae375a42a76170374d6e1952fa78d1fe4e4f756
+size 1136482241

Resources/embedders/chinese_hubert_base/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/chinese_hubert_base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fefccd26c2794a583b80f6f7210c721873cb7ebae2c1cde3baf9b27855e24d8
+size 377552987

Resources/embedders/contentvec/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.3",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/contentvec/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8dd400e054ddf4e6be75dab5a2549db748cc99e756a097c496c099f65a4854e
+size 378342945

Resources/embedders/contentvec_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
+size 189507909

Resources/embedders/hubert_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54b40fd2802423a5643779c4861af1e9ee9c1564dc9d32f54f20b5ffba7db96
+size 189507909

Resources/embedders/japanese_hubert_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dade3cf824ae0d214f7de8b73e70bae7c101e81f12d93577c4760bf516db4063
+size 378888853

Resources/embedders/japanese_hubert_base/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/japanese_hubert_base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c023ccb71e4c2b5a324c94fc5ebe12403d3081c5f370df229892419996fd113
+size 377554841

Resources/embedders/korean_hubert_base.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b42c8453b96b203198c1c280a8821158ea3fa8dbbc2a6220cad1c1489c3e65e
+size 378876997

Resources/embedders/korean_hubert_base/config.json

@@ -0,0 +1,78 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "auto_map": {
+	"FlaxAutoModel": "modeling_flax_hubert.FlaxHubertModel"
+  },
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "final_proj_size": 256,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "tokenizer_class": "Wav2Vec2CTCTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/korean_hubert_base/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931f6232879f8eadf7dbd9e00e1fa4cac61ad269af89d509b2ed75009b1a02c5
+size 377554841

Resources/embedders/spin-v2/config.json

@@ -0,0 +1,72 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/spin-v2/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a9ac0be326057b17607a988be497793817f8274e987cf691a1b61192510f823
+size 378356791

Resources/embedders/spin/config.json

@@ -0,0 +1,71 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModelWithFinalProj"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

Resources/embedders/spin/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057f12bfda54e2d486d86a52a3beb2a07c96a888bc6ac0c382c12ac18dbd500c
+size 378356791

Resources/fcpe.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8544427eebbf2baef6213cc9a05057e46961617a8e5bd96975a0d42da6a09059
+size 43362881

Resources/ffmpeg.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a4d917a444790f4c06ada640c1c0c95aecde2f8953ed8d0dfb19352500bfcd
+size 52925440

Resources/ffprobe.exe

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2da5b980a9a14a808f423d181c4ed51c2b8af11b1366699f3f7eab0609926f8f
+size 122135040

Resources/formant/stftpitchshift

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2f50ea8e5ca1a11a587f11f25ba9182f9b24e2367ac480f430b3f04062782e
+size 1822104