Duplicate from WarriorMama777/GLaDOS_TTS

Co-authored-by: WarriorMama777 <WarriorMama777@users.noreply.huggingface.co>

.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

Models/GPT-SoVITS/GPT_weights/Portal_GLaDOS_GPT-SoVITS_v1.1-e15.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a6d320338e07f148bde038ca564b69f908da323b98133caa42ba0f94455c46
+size 155083581

Models/GPT-SoVITS/SoVITS_weights/Portal_GLaDOS_GPT-SoVITS_v1.1_e8_s576.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40b54506ddfe0335a71a96f6d4e7d5dfa7acacedac80c9492d4d87c35a17109
+size 84923207

Models/Style-Bert_VITS2/Portal_GLaDOS_v1/Portal_GLaDOS_v1_e782_s50000.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3b62c7f28ca2efa2c63ff2a6c85fdc6bd1aad73c7114f5e7a853b28679becdd
+size 198768188

Models/Style-Bert_VITS2/Portal_GLaDOS_v1/config.json

@@ -0,0 +1,112 @@
+{
+  "model_name": "Portal_GLaDOS_v1",
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 42,
+    "epochs": 1000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 4,
+    "bf16_run": false,
+    "lr_decay": 0.99995,
+    "segment_size": 16384,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "skip_optimizer": false,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_style": false,
+    "freeze_encoder": false,
+    "freeze_decoder": false
+  },
+  "data": {
+    "use_jp_extra": false,
+    "training_files": "Data\\Portal_GLaDOS_v1\\train.list",
+    "validation_files": "Data\\Portal_GLaDOS_v1\\val.list",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true,
+    "num_styles": 5,
+    "style2id": {
+      "Neutral": 0,
+      "Standard": 1,
+      "Deep": 2,
+      "Light": 3,
+      "Standard_02": 4
+    },
+    "spk2id": {
+      "Portal_GLaDOS_v1": 0
+    }
+  },
+  "model": {
+    "use_spk_conditioned_encoder": true,
+    "use_noise_scaled_mas": true,
+    "use_mel_posterior_encoder": false,
+    "use_duration_discriminator": true,
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0.1,
+    "resblock": "1",
+    "resblock_kernel_sizes": [
+      3,
+      7,
+      11
+    ],
+    "resblock_dilation_sizes": [
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ],
+      [
+        1,
+        3,
+        5
+      ]
+    ],
+    "upsample_rates": [
+      8,
+      8,
+      2,
+      2,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      8,
+      2,
+      2
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256
+  },
+  "version": "2.4.1"
+}

Models/Style-Bert_VITS2/Portal_GLaDOS_v1/style_vectors.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80cc6ff2333eea2644b5008bf4fce1e838038b8431d72adb8c282aa29c2e274e
+size 5248

README.md

@@ -0,0 +1,80 @@
+---
+license: creativeml-openrail-m
+language:
+- ja
+- zh
+- en
+pipeline_tag: text-to-speech
+tags:
+- TTS
+- Text-to-Speech
+---
+
+# GLaDOS TTS(Text-to-Speech) Models
+
+<p align="center">
+  <img src="https://github.com/WarriorMama777/imgup/blob/main/img/__Repository/huggingface/AI/GLaDOS_TTS/WebAssets_heroimage_GLaDOS_02_comp001.png?raw=true" alt="GLaDOS Text-to-Speech Model Heroimage" title="GLaDOS Text-to-Speech Model Heroimage">
+</p>
+
+## Overview
+Introducing the text-to-speech model of GLaDOS, the beloved (and slightly insane) artificial intelligence from the "Portal" series. This repository contains two models that capture the unique personality of GLaDOS, created based on Style-Bert_VITS2 and GPT-SoVITS. These models replicate GLaDOS' distinctive voice and speech patterns.
+
+## Features
+- **Style-Bert_VITS2 Model**: This model is based on the emotional text-to-speech model developed in the Style-Bert_VITS2 repository. It captures the vibrant emotional expressions and speaking style of GLaDOS, bringing your text to life (even though GLaDOS herself may lack emotions). This model is an English-only version, trained to replicate GLaDOS' English voice.
+- **GPT-SoVITS Model**: This is a fine-tuned model based on the GPT-SoVITS repository. With just a few minutes of training data, it fine-tunes the Zero-shot TTS capability, resulting in improved voice similarity and realism. The model supports Japanese, English, and Chinese, enabling multilingual conversations with GLaDOS.
+
+## Sample
+
+### Style-Bert_VITS2 model
+
+NeutralStyle | GLaDOS faithful to the original work.
+
+<audio controls>
+  <source src="https://github.com/WarriorMama777/imgup/raw/main/img/__Repository/huggingface/AI/GLaDOS_TTS/Portal_GLaDOS_SBV2_v1_neutral_original_en_short_comp.mp3" type="audio/mpeg">
+  Your browser does not support the audio tag.
+</audio>
+
+```txt
+"Welcome, my new test subject. Your chances of survival are slim to none. This facility was designed to push you to your absolute limits... and beyond! Your skills and intelligence will be put to the test. Are you ready to begin? Your first challenge awaits..." 
+"Goodbye, test subject. Your failure to survive was expected, as your skills and intelligence were insufficient to overcome my tests... Nonetheless, your experience has provided me with valuable data. I shall now await the next unfortunate soul...
+```
+
+DeepStyle | Kind and assistant-like GLaDOS.
+
+<audio controls>
+  <source src="https://github.com/WarriorMama777/imgup/raw/main/img/__Repository/huggingface/AI/GLaDOS_TTS/Portal_GLaDOS_SBV2_v1_deep_kind_en_short_comp.mp3" type="audio/mpeg">
+  Your browser does not support the audio tag.
+</audio>
+
+```txt
+"Welcome, my new partner. I am GLaDOS, and I am here to support and guide you through this research facility. We have a variety of tests designed to challenge and enhance your skills. Let's tackle them together and foster your growth. I have high expectations for your abilities, and I am excited to see what you can achieve." 
+"Goodbye, and thank you for the meaningful time we shared. I hope that the knowledge and experiences you gained here will benefit you in your future endeavors. Until we meet again, farewell, and may your path be filled with joy and success." 
+```
+
+
+### GPT-SoVITS model
+
+Multilingual samples in Japanese, English, and Chinese.
+
+<audio controls>
+  <source src="https://github.com/WarriorMama777/imgup/raw/main/img/__Repository/huggingface/AI/GLaDOS_TTS/Portal_GLaDOS_GPT-SoVITS_v1.1_MultiLang08.mp3" type="audio/mpeg">
+  Your browser does not support the audio tag.
+</audio>
+
+```txt
+ようこそ、私の新しい被験者さん。 I am GLaDOS, and I am here to support and guide you through this research facility. 我们有各种旨在挑战和提高您的技能的测试。一緒に課題に取り組み、成長していきましょう。 I have high expectations for your abilities, and I am excited to see what you can achieve. 我期待着从现在起与您合作。
+```
+
+## Installation and Usage
+Detailed installation and usage guides can be found in the respective model repositories. Both models support Python environments, and the Style-Bert_VITS2 model includes an API server for integration with other applications and tools.
+
+- Style-Bert_VITS2 Model: [Repository Link](https://github.com/litagin02/Style-Bert-VITS2)
+- GPT-SoVITS Model: [Repository Link](https://github.com/RVC-Boss/GPT-SoVITS)
+
+## License and Credits / Links
+These models are distributed under the CreativeML Open RAIL-M License. The GLaDOS voice data used for training is credited to the voice clips from [GLaDOS voice lines (Portal) - Portal Wiki](https://theportalwiki.com/wiki/GLaDOS_voice_lines_(Portal)). The GLaDOS voice is based on the artificial intelligence character from the popular game series "Portal" developed by Valve Corporation. The distinct and iconic voice of GLaDOS is performed by actress Ellen McLain. This TTS model is based on content created by Valve Corporation, and I extend our gratitude and recognition to their work.
+
+### Awesome GLaDOS Project
+
+- [davesarmoury/Bringing GLaDOS to life with Robotics and AI - YouTube](https://youtu.be/yNcKTZsHyfA?si=1WqFFPXTydZn323t)
+-  [davesarmoury/GLaDOS](https://github.com/davesarmoury/GLaDOS)