Update README.md

README.md

@@ -65,9 +65,9 @@ th, td {
 <div class="box">
   <div style="margin-bottom: 20px;">
     <h2 style="margin-bottom: 4px; margin-top: 0px;">OuteAI</h2>
-    <a href="https://www.outeai.com/" target="_blank" style="margin-right: 10px;">🌎 OuteAI.com</a> 
-    <a href="https://discord.gg/vyBM87kAmf" target="_blank" style="margin-right: 10px;">🤝 Join our Discord</a>
-    <a href="https://x.com/OuteAI" target="_blank">𝕏 @OuteAI</a>
+    <a href="https://www.outeai.com/" target="_blank" style="margin-right: 10px;">🌐 OuteAI.com</a> 
+    <a href="https://discord.gg/vyBM87kAmf" target="_blank" style="margin-right: 10px;">💬 Join our Discord</a>
+    <a href="https://x.com/OuteAI" target="_blank">✖️ (Twitter) @OuteAI</a>
   </div>
   <div class="badges">
     <a href="https://huggingface.co/OuteAI/OuteTTS-0.2-500M" target="_blank" class="badge badge-hf-blue">🤗 Hugging Face - OuteTTS 0.2 500M</a>
@@ -83,7 +83,7 @@ OuteTTS-0.2-500M is our improved successor to the v0.1 release.
 The model maintains the same approach of using audio prompts without architectural changes to the foundation model itself. 
 Built upon the Qwen-2.5-0.5B, this version was trained on larger and more diverse datasets, resulting in significant improvements across all aspects of performance.
 
-Special thanks to **Hugging Face** for providing GPU grant that supported the training of this model.
+Special thanks to **Hugging Face** for providing GPU grant that supported the training of this model!
 
 ## Key Improvements
 
@@ -100,17 +100,21 @@ Special thanks to **Hugging Face** for providing GPU grant that supported the tr
 Your browser does not support the video tag.
 </video>
 
-## Usage
-
-### Installation
+## Installation
 
 [![GitHub](https://img.shields.io/badge/GitHub-OuteTTS-181717?logo=github)](https://github.com/edwko/OuteTTS)
 
 ```bash
-pip install outetts
+pip install outetts --upgrade
 ```
 
-### Interface Usage
+**Important:**
+- For GGUF support, install `llama-cpp-python` manually. [Installation Guide](https://github.com/abetlen/llama-cpp-python?tab=readme-ov-file#installation)
+- For EXL2 support, install `exllamav2` manually. [Installation Guide](https://github.com/turboderp/exllamav2?tab=readme-ov-file#installation)
+
+## Usage
+
+### Quick Start: Basic Full Example
 
 ```python
 import outetts
@@ -118,30 +122,21 @@ import outetts
 # Configure the model
 model_config = outetts.HFModelConfig_v1(
     model_path="OuteAI/OuteTTS-0.2-500M",
-    language="en",  # Supported languages in v0.2: en, zh, ja, ko
+    language="en",  # Supported languages: en, zh, ja, ko
 )
 
 # Initialize the interface
 interface = outetts.InterfaceHF(model_version="0.2", cfg=model_config)
 
-# Optional: Create a speaker profile (use a 10-15 second audio clip)
-# speaker = interface.create_speaker(
-#     audio_path="path/to/audio/file",
-#     transcript="Transcription of the audio file."
-# )
-
-# Optional: Save and load speaker profiles
-# interface.save_speaker(speaker, "speaker.json")
-# speaker = interface.load_speaker("speaker.json")
-
-# Optional: Load speaker from default presets
+# Print available default speakers
 interface.print_default_speakers()
+
+# Load a default speaker
 speaker = interface.load_default_speaker(name="male_1")
 
+# Generate speech
 output = interface.generate(
-    text="Speech synthesis is the artificial production of human speech. A computer system used for this purpose is called a speech synthesizer, and it can be implemented in software or hardware products.",
-    # Lower temperature values may result in a more stable tone,
-    # while higher values can introduce varied and expressive speech
+    text="Speech synthesis is the artificial production of human speech.",
     temperature=0.1,
     repetition_penalty=1.1,
     max_length=4096,
@@ -151,36 +146,123 @@ output = interface.generate(
     speaker=speaker,
 )
 
-# Save the synthesized speech to a file
+# Save the generated speech to a file
 output.save("output.wav")
 
-# Optional: Play the synthesized speech
+# Optional: Play the generated audio
 # output.play()
 ```
 
-## Using GGUF Model
+### Backend-Specific Configuration
+
+#### Hugging Face Transformers
+
+```python
+import outetts
+
+model_config = outetts.HFModelConfig_v1(
+    model_path="OuteAI/OuteTTS-0.2-500M",
+    language="en",  # Supported languages in v0.2: en, zh, ja, ko
+)
+
+interface = outetts.InterfaceHF(model_version="0.2", cfg=model_config)
+```
+
+#### GGUF (llama-cpp-python)
 
 ```python
-# Configure the GGUF model
+import outetts
+
 model_config = outetts.GGUFModelConfig_v1(
     model_path="local/path/to/model.gguf",
     language="en", # Supported languages in v0.2: en, zh, ja, ko
     n_gpu_layers=0,
 )
 
-# Initialize the GGUF interface
 interface = outetts.InterfaceGGUF(model_version="0.2", cfg=model_config)
 ```
 
-## Configure the model with bfloat16 and flash attention
+#### ExLlamaV2
 
 ```python
 import outetts
-import torch
 
+model_config = outetts.EXL2ModelConfig_v1(
+    model_path="local/path/to/model",
+    language="en", # Supported languages in v0.2: en, zh, ja, ko
+)
+
+interface = outetts.InterfaceEXL2(model_version="0.2", cfg=model_config)
+```
+
+### Speaker Creation and Management
+
+#### Creating a Speaker
+
+You can create a speaker profile for voice cloning, which is compatible across all backends.
+
+```python
+speaker = interface.create_speaker(
+    audio_path="path/to/audio/file.wav",
+
+    # If transcript is not provided, it will be automatically transcribed using Whisper
+    transcript=None,            # Set to None to use Whisper for transcription
+
+    whisper_model="turbo",      # Optional: specify Whisper model (default: "turbo")
+    whisper_device=None,        # Optional: specify device for Whisper (default: None)
+)
+```
+#### Saving and Loading Speaker Profiles
+
+Speaker profiles can be saved and loaded across all supported backends.
+
+```python
+# Save speaker profile
+interface.save_speaker(speaker, "speaker.json")
+
+# Load speaker profile
+speaker = interface.load_speaker("speaker.json")
+```
+
+#### Default Speaker Initialization
+
+OuteTTS includes a set of default speaker profiles. Use them directly:
+
+```python
+# Print available default speakers
+interface.print_default_speakers()
+# Load a default speaker
+speaker = interface.load_default_speaker(name="male_1")
+```
+
+### Text-to-Speech Generation
+
+The generation process is consistent across all backends.
+
+```python
+output = interface.generate(
+    text="Speech synthesis is the artificial production of human speech.",
+    temperature=0.1,
+    repetition_penalty=1.1,
+    max_length=4096,
+    speaker=speaker, # Optional: speaker profile
+)
+
+output.save("output.wav")
+# Optional: Play the audio
+# output.play()
+```
+
+### Custom Backend Configuration
+
+You can initialize custom backend configurations for specific needs.
+
+#### Example with Flash Attention for Hugging Face Transformers
+
+```python
 model_config = outetts.HFModelConfig_v1(
     model_path="OuteAI/OuteTTS-0.2-500M",
-    language="en",  # Supported languages in v0.2: en, zh, ja, ko
+    language="en",
     dtype=torch.bfloat16,
     additional_model_config={
         'attn_implementation': "flash_attention_2"
@@ -188,7 +270,7 @@ model_config = outetts.HFModelConfig_v1(
 )
 ```
 
-## Creating a Speaker for Voice Cloning
+## Speaker Profile Recommendations
 
 To achieve the best results when creating a speaker profile, consider the following recommendations: