Orpheus 3b 0.1 Ft GGUF

--- license: apache-2.0 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 --- # Orpheus 3B 0.1 ft — GGUF (ggml-quantised) 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. Key capabilities include human-like speech with natural intonation and emotion, zero-shot voice cloning, guided emotion/intonation via simple tags, and low-latency streaming (~200 ms). 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-0.1-ft-f16.gguf` | F16 | 6.16 GB | Reference quality | | `orpheus-3b-0.1-ft-q8_0.gguf` | Q8_0 | 3.70 GB | **Recommended** — ASR roundtrip word-exact vs F16 | | `orpheus-3b-0.1-ft-q4_k.gguf` | Q4_K | 2.38 GB | Smallest; smoke-tested but Q8_0 preferred | | `diff-harness-ref/orpheus-talker-ref.gguf` | — | 614 KB | Diff-harness reference checkpoint (not for inference) | The talker LM is sensitive to peaked codec distributions. Sub-Q8 quants tend to break the SNAC super-frame slot pattern and produce gibberish even when the LM perplexity remains plausible; Q4_K is provided for constrained-memory setups but Q8_0 is the safe default. ## 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-0.1-ft-GGUF orpheus-3b-0.1-ft-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-0.1-f...

Source context: 788 downloads · 1 likes · Pipeline text-to-speech · Library ggml · Repo cstr/orpheus-3b-0.1-ft-GGUF