FunASR llama.cpp runtime v0.1.9

docs(examples): add runnable Fun-ASR-Nano examples

Add runnable Python examples for quickstart, direct inference, speaker diarization, vLLM batch inference, and streaming SDK. Add examples/README.md, README links for all languages, and smoke tests covering documented example entrypoints and stale vLLM snippets.

docs(examples): add runnable Fun-ASR-Nano examples

Add runnable Python examples for quickstart, direct inference, speaker diarization, vLLM batch inference, and streaming SDK. Add examples/README.md, README links for all languages, and smoke tests covering documented example entrypoints and stale vLLM snippets.

docs(README): promote llama.cpp/GGUF (CPU/edge) runtime to a first-cl…

…ass section (#125)

test: numerical regression harness (frozen golden vs ggml/VAD/CIF/CTC…

… output) (#124)

Adds tests/ — runs each runtime tool on a fixed 6 s clip and diffs against frozen
golden output, catching regressions in the ggml graphs, the FSMN-VAD state machine,
the CIF predictor and CTC decode.

- tests/run_regression.sh: auto-detects which tools are built; VAD model is auto-fetched
  (1.7 MB), ASR GGUFs tested when present or with RUN_FULL=1 (downloads from HF).
  Non-zero exit on any mismatch. BIN_DIR/MODELS_DIR overridable.
- tests/sample.wav (~6 s) + tests/golden/*.txt: golden captured on Linux x86-64 with the
  f16 GGUFs from FunAudioLLM/*-GGUF.

Verified locally: all present tools PASS; default mode fetches VAD + skips absent models.

docs: sync vllm_guide.md - add GLM-ASR benchmark (RTFx=263, community…

… model) (#105)

Co-authored-by: xiaoyunchong.xyc <xiaoyunchong.xyc@alibaba-inc.com>