Command-Line Interface
Entry point model
Hyperion CLI commands are generated from scripts in hyperion.bin
(hyperion/bin on disk).
Generation flow:
proto_pyproject.tomldefines static package metadata template.generate_pyproject.pyscanshyperion/bin/*.py.Each script is mapped to
hyperion-<script-name>inpyproject.toml.Dependencies are loaded from
requirements.txt.
The machine-readable classification source is docs/cli_inventory.json. It
contains one record for every maintained executable module in hyperion/bin:
the installed command name, task family, stable/experimental status, planned
guide page, and optional runtime requirements. Later CLI reference pages and CI
checks are generated from or validated against this inventory.
Regenerate entry points with:
python generate_pyproject.py
Naming convention
A script file like hyperion/bin/train_qvector.py becomes command:
hyperion-train-qvector
Task-oriented command index
The following complete index is generated from docs/cli_inventory.json.
Stable commands are supported public interfaces. Experimental commands are
visible for evaluation, but their configuration and checkpoint compatibility
are not guaranteed across minor releases. Family guides with full workflows
are linked below.
Training
Model and backend training commands.
Read the training guide.
Stable commands:
hyperion-make-wav2xvectorConditional runtime requirements: PyTorch.hyperion-train-dino-wav2xvectorConditional runtime requirements: PyTorch.hyperion-train-lgbehyperion-train-pldahyperion-train-qmfhyperion-train-verification-calibrationhyperion-train-verification-greedy-fusionhyperion-train-wav2vec2xvectorConditional runtime requirements: PyTorch, transformers.hyperion-train-wav2xvectorConditional runtime requirements: PyTorch.hyperion-train-xvector-from-wavConditional runtime requirements: PyTorch.
Experimental commands:
hyperion-train-dacConditional runtime requirements: PyTorch, codec training data.hyperion-train-freevcConditional runtime requirements: PyTorch, VITS/FreeVC assets.hyperion-train-qvectorConditional runtime requirements: PyTorch.hyperion-train-tokenizerConditional runtime requirements: PyTorch, codec training data.hyperion-train-vi-anonymizerConditional runtime requirements: PyTorch, VITS assets.hyperion-train-vi-emo-normalizerConditional runtime requirements: PyTorch, VITS assets.hyperion-train-wav2rnn-transducerConditional runtime requirements: k2, PyTorch, transducer training data.hyperion-train-wav2vec2rnn-transducerConditional runtime requirements: k2, PyTorch, transformers, transducer training data.hyperion-train-wav2vec2transducerConditional runtime requirements: k2, PyTorch, transformers, transducer training data.
Fine-tuning and adaptation
Checkpoint adaptation and fine-tuning commands.
Read the fine-tuning and adaptation guide.
Stable commands:
hyperion-adv-finetune-xvector-from-wavConditional runtime requirements: PyTorch.hyperion-finetune-wav2vec2xvectorConditional runtime requirements: PyTorch, transformers.hyperion-finetune-wav2xvectorConditional runtime requirements: PyTorch.hyperion-finetune-xvector-dfr-from-wavConditional runtime requirements: PyTorch.hyperion-finetune-xvector-from-wavConditional runtime requirements: PyTorch.
Experimental commands:
hyperion-finetune-dacConditional runtime requirements: PyTorch, codec checkpoint.hyperion-finetune-qvectorConditional runtime requirements: PyTorch, Q-vector checkpoint.hyperion-finetune-vi-anonymizerConditional runtime requirements: PyTorch, VITS checkpoint.hyperion-finetune-wav2vec2transducerConditional runtime requirements: k2, PyTorch, transformers, transducer checkpoint.
Extraction and inference
Embedding extraction, model inference, and decoding commands.
Read the extraction and inference guide.
Stable commands:
hyperion-eval-wav2vec2xvector-logitsConditional runtime requirements: PyTorch, transformers.hyperion-eval-wav2xvector-logitsConditional runtime requirements: PyTorch.hyperion-eval-xvec-logits-from-wavConditional runtime requirements: PyTorch.hyperion-extract-wav2vec2xvectorsConditional runtime requirements: PyTorch, transformers.hyperion-extract-wav2xvectorsConditional runtime requirements: PyTorch.hyperion-extract-xvectors-from-wavConditional runtime requirements: PyTorch.hyperion-extract-xvectors-slidwin-from-wavConditional runtime requirements: PyTorch.
Experimental commands:
hyperion-infer-qvectorsConditional runtime requirements: PyTorch, Q-vector checkpoint.
Backends, scoring, and evaluation
Backend fitting, scoring, calibration, fusion, and evaluation commands.
Read the backends, scoring, and evaluation guide.
Stable commands:
hyperion-accum-speech-quality-metricsConditional runtime requirements: ONNX Runtime, speech-quality metric dependencies.hyperion-accum-voxprofile-metricsConditional runtime requirements: voxprofile extra.hyperion-cluster-embeddingshyperion-eval-cosine-scoring-backendhyperion-eval-cosine-scoring-backend-with-qmfhyperion-eval-lgbehyperion-eval-plda-backendhyperion-eval-speech-quality-metricsConditional runtime requirements: ONNX Runtime, TPM model packages, optional quality model assets.hyperion-eval-verification-anonymization-metricshyperion-eval-verification-calibrationhyperion-eval-verification-greedy-fusionhyperion-eval-verification-metricshyperion-eval-voxprofile-metricsConditional runtime requirements: voxprofile extra, VoxProfile model assets.hyperion-eval-xvec-cosine-scoring-from-adv-test-wavConditional runtime requirements: PyTorch.hyperion-eval-xvec-cosine-scoring-from-adv-test-wav-waveganConditional runtime requirements: PyTorch.hyperion-eval-xvec-cosine-scoring-from-art-test-wavConditional runtime requirements: ART, PyTorch.hyperion-eval-xvec-cosine-scoring-from-test-wavConditional runtime requirements: PyTorch.hyperion-eval-xvec-cosine-scoring-from-transfer-adv-test-wavConditional runtime requirements: PyTorch.hyperion-eval-xvec-cosine-scoring-from-transfer-art-test-wavConditional runtime requirements: ART, PyTorch.hyperion-generate-adv-attacks-xvector-classifConditional runtime requirements: PyTorch.hyperion-generate-adv-attacks-xvector-verifConditional runtime requirements: PyTorch.
Data preparation and manifest operations
Corpus preparation, dataset/table management, and metadata generation commands.
Read the data preparation and manifest operations guide.
Stable commands:
hyperion-datasethyperion-prepare-dataConditional runtime requirements: dataset-specific corpus files.hyperion-split-dataset-into-trials-and-cohorthyperion-tables
Audio, feature, and VAD conversion
Audio, feature, VAD, and score/trial conversion commands.
Read the audio, feature, and vad conversion guide.
Stable commands:
hyperion-apply-mvn-select-frameshyperion-audio-to-durationConditional runtime requirements: audio backend.hyperion-compute-energy-vadConditional runtime requirements: audio backend.hyperion-compute-mfcc-featsConditional runtime requirements: audio backend.hyperion-convert-vad-formathyperion-copy-featshyperion-make-babble-noise-audio-filesConditional runtime requirements: audio backend.hyperion-pack-wav-rirsConditional runtime requirements: audio backend.hyperion-preprocess-audio-filesConditional runtime requirements: audio backend.
Visualization and utilities
Analysis, plotting, merging, and other standalone utilities.
Read the visualization and utilities guide.
Stable commands:
hyperion-merge-scoreshyperion-merge-trialshyperion-plot-embedding-tsneConditional runtime requirements: matplotlib, scikit-learn.hyperion-plot-embedding-tsne-per-classConditional runtime requirements: matplotlib, scikit-learn.hyperion-submitConditional runtime requirements: Slurm (slurm backend only).
Family guides
Generated command and option reference
The complete parser-derived option reference is generated from command
--help output. It is included separately because it is intentionally an
exact parser snapshot rather than a task guide:
Scope notes
hyperion/bin_deprecandhyperion/bin_deprec2are deprecated and not part of the documented CLI surface.Experimental transducer decoders are listed in Experimental Components.
Optional dependencies and TPM commands
The generated index labels conditional runtime requirements: dependencies, extras, model assets, or network retrieval needed for that command, but not for every Hyperion workflow. This does not promise that an asset is installed, licensed, available offline, or compatible with an arbitrary device.
The policy for package extras, local assets, first-run downloads, offline execution, and stable TPM wrappers is defined in Optional Dependencies, External Assets, and TPM. For reproducible work, provide local assets and pin model revisions rather than depending on a mutable remote default or a personal cache.
Discover commands
After installation:
python -m pip show hyperion-ml
hyperion-train-qvector --help
hyperion-eval-verification-metrics --help