1 Pull request merged by 1 person

• docs: update README.md

  #25 merged Mar 23, 2025

3 Pull requests opened by 3 people

• fix: Issue when running example script in debugging mode

  #46 opened Mar 23, 2025

• wip

  #58 opened Mar 26, 2025

• Add a Streaming Example for not GPU-users

  #60 opened Mar 26, 2025

37 Issues closed by 12 people

• How to achieve minimal latency?

  #61 closed Mar 27, 2025

• Pre-training datasets samples

  #20 closed Mar 25, 2025

• Will this work on a mac?

  #56 closed Mar 25, 2025

• Slow audio generation on A10G and A100

  #53 closed Mar 25, 2025

• vllm usage

  #22 closed Mar 24, 2025

• Pretraining Cost Estimate for New Language

  #52 closed Mar 24, 2025

• Zero Shot Voice Cloning?

  #50 closed Mar 24, 2025

• How can I generate response in streaming way?

  #51 closed Mar 24, 2025

• Emotion of Speech

  #55 closed Mar 24, 2025

• No module named 'orpheus_tts'

  #49 closed Mar 24, 2025

• Data donation

  #26 closed Mar 24, 2025

• Please support Pascal cards

  #45 closed Mar 24, 2025

• Speech Duration

  #48 closed Mar 24, 2025

• About 400m and 150m model

  #47 closed Mar 24, 2025

• Compute capability

  #44 closed Mar 23, 2025

• Pre-train Data Structure

  #37 closed Mar 23, 2025

• Huge GPU memory

  #42 closed Mar 23, 2025

• peft with unsloth

  #40 closed Mar 22, 2025

• How to convert to ONNX ?

  #35 closed Mar 21, 2025

• Does it only support English

  #34 closed Mar 21, 2025

• about the training on text tokens

  #36 closed Mar 21, 2025

• Multilanguages?

  #38 closed Mar 21, 2025

• How do I force it to run on CPU?

  #23 closed Mar 21, 2025

• Getting error during Lora finetuning

  #31 closed Mar 20, 2025

• No module named 'vllm._C

  #5 closed Mar 20, 2025

• No module named 'vllm._C'

  #32 closed Mar 20, 2025

• Open-source license for Orpheus-TTS?

  #33 closed Mar 20, 2025

• What is the license for the code and the models?

  #24 closed Mar 20, 2025

• Voice name model parametrization

  #28 closed Mar 20, 2025

• License?

  #29 closed Mar 20, 2025

• Finetuning with voice name

  #30 closed Mar 20, 2025

• TypeError: an integer is required

  #27 closed Mar 20, 2025

• Can't Load Tokenizer for Checkpoint in Orpheus-TTS after Finetune

  #21 closed Mar 20, 2025

• Brilliant work! Is other languages support?

  #19 closed Mar 20, 2025

• Fine tuning

  #18 closed Mar 20, 2025

• tp

  #16 closed Mar 20, 2025

• Question about emotion tags

  #15 closed Mar 20, 2025

7 Issues opened by 6 people

• Rust macOS accelerated inference of Orpheus based on Candle

  #59 opened Mar 26, 2025

• 500M model release date

  #57 opened Mar 25, 2025

• PyTorch Build Lacks Support for NVIDIA GeForce RTX 5080 (sm_120) Causing TTS Generation Failure

  #54 opened Mar 24, 2025

• Stream text into KV Cache

  #43 opened Mar 23, 2025

• Will there be a way to identify the output as being generated by this tool?

  #41 opened Mar 22, 2025

• Feature request: Allow generating subtitles along

  #39 opened Mar 21, 2025

• Colab has a few issues

  #17 opened Mar 20, 2025

5 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• We talk about the model here!

  #4 commented on Mar 20, 2025 • 0 new comments

• Zero-Shot Voice Cloning

  #6 commented on Mar 25, 2025 • 0 new comments

• VRAM Requirements?

  #9 commented on Mar 20, 2025 • 0 new comments

• training / finetuning other languages

  #10 commented on Mar 25, 2025 • 0 new comments

• vLLM error (max seq len/KV cache)

  #13 commented on Mar 26, 2025 • 0 new comments