Nnow2024's picture
Upload folder using huggingface_hub
bea46ac verified
|
Raw
History Blame Contribute Delete
1.6 kB

External model assets

models/ is a deployment directory, not a source-controlled package and not a wheel payload. Set AX_MODEL_DIR to this directory (or an identically laid out copy) at runtime.

The authoritative inventory is src/ax_meeting_cpp/resources/model_assets.json. It records every required file's relative path, byte size and SHA-256 for the two ASR choices:

  • sensevoice: standard ASR plus word timestamps.
  • firered_punc: FireRed AED and CT-Transformer punctuation (no word timings).

The required layout is deliberately grouped by model family:

models/
β”œβ”€β”€ vad/          # vad.axmodel, CMVN, config
β”œβ”€β”€ cam++/        # CAM++ speaker embedding model
β”œβ”€β”€ sensevoice/   # model, CMVN/config, BPE and language queries
β”œβ”€β”€ fireredasr/   # FireRed encoder/decoder, CMVN, dictionary, BPE, PE
└── punc/         # CT-Transformer model and vocabulary

Before deploying a copied bundle, verify its integrity without loading any model:

python3 tools/verify_assets.py \
  --manifest src/ax_meeting_cpp/resources/model_assets.json \
  --root /opt/ax-meeting/models --backend firered_punc

The default check only requires the declared files to exist. Add --verify-size --verify-sha256 when an exact supplied asset set must be audited; hashes are informative rather than a runtime or build prerequisite.

Model files retain their upstream terms. The source-code MIT license neither grants model redistribution rights nor asserts a license that was not supplied with the assets.