Prince-1/orpheus_3b_0.1_GGUF

Uploaded model

• Finetuned by: Prince-1
• License: apache-2.0
• Finetuned from model : unsloth/orpheus-3b-0.1-ft-unsloth-bnb-4bit

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances.

Model Details

Model Capabilities

• Human-Like Speech: Natural intonation, emotion, and rhythm that is superior to SOTA closed source models
• Zero-Shot Voice Cloning: Clone voices without prior fine-tuning
• Guided Emotion and Intonation: Control speech and emotion characteristics with simple tags
• Low Latency: ~200ms streaming latency for realtime applications, reducible to ~100ms with input streaming

Model Sources

• GitHub Repo: https://github.com/canopyai/Orpheus-TTS
• Blog Post: https://canopylabs.ai/model-releases
• Colab Inference Notebook: notebook link

Quantization

Model is converted into GGUF

Choose quantization_method to be:

• not_quantized: Recommended. Fast conversion. Slow inference, big files.
• fast_quantized: Recommended. Fast conversion. OK inference, OK file size.
• quantized: Recommended. Slow conversion. Fast inference, small files.
• f32: Not recommended. Retains 100% accuracy, but super slow and memory hungry.
• f16: Fastest conversion + retains 100% accuracy. Slow and memory hungry.
• q8_0: Fast conversion. High resource use, but generally acceptable.
• q4_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.
• q5_k_m: Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.
• q2_k: Uses Q4_K for attention.vw and feed_forward.w2 tensors, Q2_K for the other tensors.
• q3_k_l: Uses Q5_K for attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K.
• q3_k_m: Uses Q4_K for attention.wv, attention.wo, and feed_forward.w2 tensors, else Q3_K.
• q3_k_s: Uses Q3_K for all tensors.
• q4_0: Original quant method, 4-bit.
• q4_1: Higher accuracy than q4_0 but not as high as q5_0. However, has quicker inference than q5 models.
• q4_k_s: Uses Q4_K for all tensors.
• q4_k: Alias for q4_k_m.
• q5_k: Alias for q5_k_m.
• q5_0: Higher accuracy, higher resource usage and slower inference.
• q5_1: Even higher accuracy, resource usage and slower inference.
• q5_k_s: Uses Q5_K for all tensors.
• q6_k: Uses Q8_K for all tensors.

Usage

The model is utilse using module [llama-cpp-python](https://github.com/abetlen/llama-cpp-python] module) which provide python binding for llama-cpp.

from llama-cpp-python import LLM 

Model Misuse

Do not use our models for impersonation without consent, misinformation or deception (including fake news or fraudulent calls), or any illegal or harmful activity. By using this model, you agree to follow all applicable laws and ethical guidelines. We disclaim responsibility for any use.