StyleTTS (multi, vi)

multi/StyleTTS2-LibriTTS/.gitattributes

@@ -0,0 +1,35 @@
+*.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

multi/StyleTTS2-LibriTTS/Models/LibriTTS/config.yml

@@ -0,0 +1,21 @@
+{ASR_config: Utils/ASR/config.yml, ASR_path: Utils/ASR/epoch_00080.pth, F0_path: Utils/JDC/bst.t7,
+  PLBERT_dir: Utils/PLBERT/, batch_size: 8, data_params: {OOD_data: Data/OOD_texts.txt,
+    min_length: 50, root_path: '', train_data: Data/train_list.txt, val_data: Data/val_list.txt},
+  device: cuda, epochs_1st: 40, epochs_2nd: 25, first_stage_path: first_stage.pth,
+  load_only_params: false, log_dir: Models/LibriTTS, log_interval: 10, loss_params: {
+    TMA_epoch: 4, diff_epoch: 0, joint_epoch: 0, lambda_F0: 1.0, lambda_ce: 20.0,
+    lambda_diff: 1.0, lambda_dur: 1.0, lambda_gen: 1.0, lambda_mel: 5.0, lambda_mono: 1.0,
+    lambda_norm: 1.0, lambda_s2s: 1.0, lambda_slm: 1.0, lambda_sty: 1.0}, max_len: 300,
+  model_params: {decoder: {resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3,
+          5]], resblock_kernel_sizes: [3, 7, 11], type: hifigan, upsample_initial_channel: 512,
+      upsample_kernel_sizes: [20, 10, 6, 4], upsample_rates: [10, 5, 3, 2]}, diffusion: {
+      dist: {estimate_sigma_data: true, mean: -3.0, sigma_data: 0.19926648961191362,
+        std: 1.0}, embedding_mask_proba: 0.1, transformer: {head_features: 64, multiplier: 2,
+        num_heads: 8, num_layers: 3}}, dim_in: 64, dropout: 0.2, hidden_dim: 512,
+    max_conv_dim: 512, max_dur: 50, multispeaker: true, n_layer: 3, n_mels: 80, n_token: 178,
+    slm: {hidden: 768, initial_channel: 64, model: microsoft/wavlm-base-plus, nlayers: 13,
+      sr: 16000}, style_dim: 128}, optimizer_params: {bert_lr: 1.0e-05, ft_lr: 1.0e-05,
+    lr: 0.0001}, preprocess_params: {spect_params: {hop_length: 300, n_fft: 2048,
+      win_length: 1200}, sr: 24000}, pretrained_model: Models/LibriTTS/epoch_2nd_00002.pth,
+  save_freq: 1, second_stage_load_pretrained: true, slmadv_params: {batch_percentage: 0.5,
+    iter: 20, max_len: 500, min_len: 400, scale: 0.01, sig: 1.5, thresh: 5}}

multi/StyleTTS2-LibriTTS/Models/LibriTTS/epochs_2nd_00020.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1164ffe19a17449d2c722234cecaf2836b35a698fb8ffd42562d2663657dca0a
+size 771390526

multi/StyleTTS2-LibriTTS/README.md

@@ -0,0 +1,100 @@
+---
+language:
+- en
+- multilingual
+tags:
+- text-to-speech
+- speech-synthesis
+- pytorch
+- styletts2
+- speaches
+- neural-tts
+- voice-cloning
+pipeline_tag: text-to-speech
+library_name: pytorch
+license: mit
+datasets:
+- LibriTTS
+metrics:
+- naturalness
+- similarity
+widget:
+- text: "Hello, this is a sample of StyleTTS2 speech synthesis."
+  example_title: "English Sample"
+- text: "StyleTTS2 can synthesize high-quality speech with style control."
+  example_title: "Style Control Sample"
+---
+
+# StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training
+
+StyleTTS 2 is a text-to-speech model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level text-to-speech synthesis. This model builds upon the original StyleTTS with significant improvements in naturalness and similarity.
+
+## Model Description
+
+- **Model Type**: Neural Text-to-Speech (TTS)
+- **Language(s)**: English (primary), with support for 18+ languages
+- **License**: MIT
+- **Paper**: [StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training](https://arxiv.org/abs/2306.07691)
+- **Sample Rate**: 24,000 Hz
+- **Architecture**: Style diffusion with adversarial training
+
+## Features
+
+- **High-Quality Synthesis**: Achieves human-level naturalness in speech synthesis
+- **Style Control**: Advanced style transfer and voice cloning capabilities
+- **Multi-Language Support**: Primary English model with support for 18+ additional languages
+- **Voice Cloning**: Can clone voices from reference audio samples
+- **Diffusion-Based**: Uses diffusion models for high-quality audio generation
+
+## Usage
+
+This model is designed for text-to-speech synthesis with the following capabilities:
+
+1. **Multi-Voice Synthesis**: Generate speech using preset voice styles
+2. **Voice Cloning**: Clone voices from reference audio samples
+3. **Style Control**: Fine-tune synthesis parameters for different styles
+4. **Multi-Language**: Support for various languages with English-accented pronunciation
+
+### Parameters
+
+- `alpha` (0.0-1.0): Style blending factor (default: 0.3)
+- `beta` (0.0-1.0): Style mixing factor (default: 0.7)
+- `diffusion_steps` (3-20): Number of diffusion steps for quality (default: 5)
+- `embedding_scale` (1.0-10.0): Embedding scale factor (default: 1.0)
+
+## Training Data
+
+- **Primary Dataset**: LibriTTS
+- **Languages**: English (primary) + 18 additional languages
+- **Training Approach**: Style diffusion with adversarial training using large speech language models
+
+## Performance
+
+StyleTTS 2 achieves human-level performance in:
+- **Naturalness**: Comparable to human speech in listening tests
+- **Similarity**: High fidelity voice cloning and style transfer
+- **Quality**: Superior audio quality compared to previous TTS models
+
+## Limitations
+
+- **Compute Requirements**: Requires significant computational resources for inference
+- **English-First**: Optimized for English, other languages may have accented pronunciation
+- **Context Dependency**: Performance varies with input text length and complexity
+
+## Citation
+
+```bibtex
+@article{li2024styletts2,
+  title={StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models},
+  author={Li, Yinghao Aaron and Han, Cong and Mesgarani, Nima},
+  journal={arXiv preprint arXiv:2306.07691},
+  year={2024}
+}
+```
+
+## Links
+
+- Paper: [https://arxiv.org/abs/2306.07691](https://arxiv.org/abs/2306.07691)
+- Samples: [https://styletts2.github.io/](https://styletts2.github.io/)
+- Code: [https://github.com/yl4579/StyleTTS2](https://github.com/yl4579/StyleTTS2)
+- License: MIT License

multi/StyleTTS2-LibriTTS/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/jakezp/StyleTTS2-LibriTTS

vi/styletts2_vi/.gitattributes

@@ -0,0 +1,35 @@
+*.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

vi/styletts2_vi/epoch_2nd_00058.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a0724294b5caed11b883225f34c86d1344784dad699c32782167737b513bc3
+size 2132463654

vi/styletts2_vi/gemini_2nd_00045.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:508a27f84a55d636e2cfa5b7ea15b6a1e93bb817e17793d1358457ede5d5ce09
+size 2132463590

vi/styletts2_vi/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/ltphuongunited/styletts2_vi