Orpheus 3b Base GGUF

--- license: llama3.2 language: - en base_model: - canopylabs/orpheus-3b-0.1-ft - unsloth/orpheus-3b-0.1-ft - meta-llama/Llama-3.2-3B-Instruct pipeline_tag: text-to-speech tags: - tts - text-to-speech - orpheus - llama - snac - gguf - crispasr library_name: ggml --- # [DEPRECATED] Orpheus 3B — GGUF (ggml-quantised) > **This repo is deprecated.** Use [`cstr/orpheus-3b-0.1-ft-GGUF`](https://huggingface.co/cstr/orpheus-3b-0.1-ft-GGUF) instead — it has F16 + Q8_0 + Q4_K quants plus the diff-harness reference file. CrispASR's model registry and auto-download now point there. GGUF / ggml conversion of [`canopylabs/orpheus-3b-0.1-ft`](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft) (sourced via the non-gated [`unsloth/orpheus-3b-0.1-ft`](https://huggingface.co/unsloth/orpheus-3b-0.1-ft) mirror) for use with **[CrispStrobe/CrispASR](https://github.com/CrispStrobe/CrispASR)**. Orpheus 3B is a Llama-3.2-3B-Instruct talker finetuned to emit `<custom_token_N>` codec tokens that the SNAC 24 kHz codec decodes back to speech. Distributed under the **Llama-3.2 community license** ("Built with Llama"). 8 fixed English speakers (`tara, leah, jess, leo, dan, mia, zac, zoe`). Pair this with the SNAC codec at [`cstr/snac-24khz-GGUF`](https://huggingface.co/cstr/snac-24khz-GGUF) — the talker outputs codec tokens but doesn't render audio without it. ## Files | File | Quant | Size | Notes | |---|---|---:|---| | `orpheus-3b-base-f16.gguf` | F16 | 6.2 GB | Reference quality | | `orpheus-3b-base-q8_0.gguf` | Q8_0 | 3.4 GB | **Recommended** — ASR roundtrip word-exact vs F16 | The talker LM is sensitive to peaked codec distributions, so we ship F16 + Q8_0 only. Sub-Q8 quants tend to break the SNAC super-frame slot pattern and produce gibberish even when the LM perplexity remains plausible. ## Quick start ```bash # 1. Build CrispASR git clone https://github.com/CrispStrobe/CrispASR cd CrispASR cmake -B build -DCMAKE_BUILD_TYPE=Release cmake --build build -j --target crispasr-lib # 2. Pull the talker + the SNAC codec huggingface-cli download cstr/orpheus-3b-base-GGUF orpheus-3b-base-q8_0.gguf --local-dir . huggingface-cli download cstr/snac-24khz-GGUF snac-24khz.gguf --local-dir . # 3. Synthesise ./build/bin/crispasr --backend orpheus \ -m orpheus-3b-base-q8_0.gguf \ --codec-model snac-24khz.gguf \ --voice tara \ --temperature 0.6 \ --tts "Hello, my name is Tara."...

Source context: 596 downloads · 1 likes · Pipeline text-to-speech · Library ggml · Repo cstr/orpheus-3b-base-GGUF