Zum Inhalt

VoiceHubvui

Vui

Uses Vui's bounded chunk retry and duration controls with the registered pinned artifacts.

Text to speechVoiceHub-nativevuiParameters: Not reportedLanguage: enTraining: preprocessedLicense: Checkpoint-specific

Parameter metadata: Not reported: the audited metadata available for the registered default does not provide an exact parameter total.

Use this model
Resources
Upstream GitHub VoiceHub source

Usage

Complete the VoiceHub installation once, then run this repository-authored example. Model pages intentionally contain no package-install command.

This example is maintained against VoiceHub's public API; it is not copied from an upstream demo or package README.

Model-specific path: Uses Vui's bounded chunk retry and duration controls with the registered pinned artifacts.

Inputs and controls: The short registry alias resolves the model and Fluac codec from one immutable repository snapshot.

from pathlib import Path

from voicehub import AutoModelForTextToSpeech, TTSGenerationConfig

model = AutoModelForTextToSpeech.from_pretrained(
    'vui-abraham-100m.pt',
    model_type='vui',
    device="cuda",
    lazy_load=True,
)
output = model.generate(
    'VoiceHub keeps model integrations explicit and reproducible.',
    generation_config=TTSGenerationConfig(
        seed=42,
        output_file=Path("output.wav"),
    ),
    max_secs=20,
    max_chunk_retries=3,
    temperature=0.5,
    top_k=100,
)
print(output.file_path, output.sample_rate, output.metadata)

Use authorized recordings. Verify hardware needs and pin a revision in production.

Overview

vui is a VoiceHub text to speech integration. This page is generated from its registry contract.

Property Value
Task Text to speech
Architecture vui
Runtime VoiceHub-native
Languages en
Capabilities text-to-speech, fine-tuning, safetensors, standalone-safetensors-export, voicehub-native, native-runtime, preprocessed-training
Reusable components —
Normalized output TTSOutput

Language support

Supported language abbreviations

en

Paper and GitHub

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('vui')
print(config.model_type)
Property Value
Canonical model type vui
Configuration class VuiConfig
Architecture class VuiForTextToSpeech

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'vui-abraham-100m.pt',
    model_type='vui',
)
print(type(processor).__name__)

Inference

The Usage example returns TTSOutput through AutoModelForTextToSpeech.

Input and output contract

Property Value
Readiness preprocessed
Data architecture codec-lm
Sample rate 44,100 Hz
Contract getter get_tts_dataset_spec('vui')
Variant Required fields One of Boundary Other rules
codec-batch input_ids, audio_codes — Prepared —

Autoregressive text/audio-token or codec-language-model data. See the data workflow.

Training and optimization

Use available_optimization_passes() to discover reversible public passes. Unsupported runtime or hardware fails closed before mutation.

Training contract

Property Value
Support preprocessed
Family causal-lm
Recipe single-phase
Default phase codec_language_model
Training checkpoint vui-abraham-100m.pt
Native training graph yes
Phase Kind Components Required inputs Loss keys
codec_language_model objective model input_ids, audio_codes loss, codec_ce_loss

Prepare the exact tensors listed in the data contract before this step. Call model.validate_training_support() first, then follow the training workflow.

Checkpoints, provenance, license, and limitations

Property Value
Default checkpoint vui-abraham-100m.pt
Hugging Face ID fluxions/vui
Official Vui repository, verified available on 2026-08-11; VoiceHub resolves the registered filename and pinned revision from this repo.
Checkpoint status Registry default; pin an immutable revision for production and reproducible evidence
Optional dependency extra Core package
Hardware and runtime Usage selects cuda; verify checkpoint-specific requirements
Real-checkpoint evidence Release evidence; a registry default alone is not execution evidence
Implementation voicehub.models.vui.modeling_vui.VuiForTextToSpeech
Configuration voicehub.models.vui.configuration_vui.VuiConfig
Source provenance voicehub/models/vui/SOURCE.json
License Checkpoint-specific

No VoiceHub-specific license override is registered. Verify the checkpoint and upstream source terms before use.

Confirm the checkpoint revision, access terms, provenance, and license.

Limitations

  • No integration-specific checkpoint limitation is registered. Verify the selected checkpoint revision and its documented runtime requirements.
  • Validate memory, precision, and optional dependencies on the target system.
  • Public optimizations fail closed when the runtime or hardware cannot satisfy their validation contract; an unavailable pass is not reported as applied.
  • Contract tests do not replace the linked released-checkpoint evidence.

Public API

Use the stable configuration, processor, and task-model facades below.

Configuration

VuiConfig

View source

VuiConfig(**config_kwargs)

Parameters

  • **config_kwargs — Configuration fields validated by VuiConfig.

Model

VuiForTextToSpeech

View source

AutoModelForTextToSpeech.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='vui',
    config=None,
    **model_kwargs,
)

Parameters

  • pretrained_model_name_or_path — Hub ID or compatible local directory.
  • model_type — Canonical model type; use 'vui'.
  • config — Optional preloaded VuiConfig instance.
  • **model_kwargs — Model-specific loading arguments.
from voicehub import get_model_spec

spec = get_model_spec('vui')
print(spec.display_name, spec.task.value)
Purpose Public object
Discover get_model_spec('vui')
Load and run AutoModelForTextToSpeech
Configure VuiConfig
Process AutoProcessor
Model implementation VuiForTextToSpeech
Normalized output TTSOutput
Training contract get_training_spec('vui')
Optimization lifecycle available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

See all model guides, inference, and the training matrix.