| --- |
| license: llama3.2 |
| datasets: |
| - ylacombe/google-argentinian-spanish |
| language: |
| - es |
| base_model: |
| - canopylabs/3b-es_it-ft-research_release |
| pipeline_tag: text-to-speech |
| library_name: transformers |
| tags: |
| - text-to-speech |
| - rioplatense |
| - argentinian |
| - speech |
| --- |
| |
| # Orpheus 3B Rioplatense Spanish finetune |
|
|
| Orpheus TTS is a Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned from [canopylabs/3b-es_it-ft-research_release](https://huggingface.co/canopylabs/3b-es_it-ft-research_release) with [ylacombe/google-argentinian-spanish](https://huggingface.co/datasets/ylacombe/google-argentinian-spanish) to deliver human-level, Rioplatense accent speech synthesis, achieving clarity, expressiveness, and real-time streaming performances. |
|
|
| Find an inference API endpoint for this model at [surus](https://surus.dev/)! Sign up and get free credits to test out this and other SoTA LM models! |
|
|
| # 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](https://github.com/canopyai/Orpheus-TTS) |
| - **Blog Post:** [https://canopylabs.ai/model-releases](https://canopylabs.ai/releases/orpheus_can_speak_any_language) |
| - **Colab Inference Notebook:** [notebook link](https://colab.research.google.com/drive/1KhXT56UePPUHhqitJNUxq63k-pQomz3N?usp=sharing) |
|
|
|
|
| # Usage |
|
|
| Check out Colab ([link to Colab](https://colab.research.google.com/drive/1KhXT56UePPUHhqitJNUxq63k-pQomz3N?usp=sharing)) or GitHub ([link to GitHub](https://github.com/canopyai/Orpheus-TTS)) on how to run easy inference on our finetuned models. |
|
|
|
|
| # 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. |
