Copy page

ESespnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best

ESPnetASR

Uses the audited ESPnet LibriSpeech transformer with an explicit beam size.

Automatic speech recognitionVoiceHub-nativeespnet-librispeech-transformer-e18Parameters: Not reportedLanguage: enTraining: nativeLicense: Checkpoint-specific

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

Use this model Copy model ID Checkpoint

Resources

Paper Upstream GitHub VoiceHub source Open in Colab

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 the audited ESPnet LibriSpeech transformer with an explicit beam size.

Inputs and controls: This release is English-only and has no calibrated timestamp head.

from pathlib import Path

from voicehub import AutoModelForSpeechRecognition

AUDIO_FILE = Path("speech.wav")
if not AUDIO_FILE.is_file():
    raise FileNotFoundError(AUDIO_FILE)

model = AutoModelForSpeechRecognition.from_pretrained(
    'espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best',
    model_type='asr_espnet',
    device="cuda",
    lazy_load=True,
)
output = model.transcribe(
    AUDIO_FILE,
    language="en",
    num_beams=10,
)
print(output.text)
for segment in output.segments:
    print(segment.start, segment.end, segment.text, segment.confidence)

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

Overview

asr_espnet is a VoiceHub automatic speech recognition integration. This page is generated from its registry contract. Open the asr_espnet Colab notebook.

Property	Value
Task	Automatic speech recognition
Architecture	espnet-librispeech-transformer-e18
Runtime	VoiceHub-native
Languages	en
Capabilities	automatic-speech-recognition, english, safetensors, fine-tuning, voicehub-native, native-runtime, raw-audio-fine-tuning, hybrid-ctc-attention
Reusable components	—
Normalized output	ASROutput

Language support

Supported language abbreviations

en

Paper and GitHub

• Paper: ESPnet: End-to-End Speech Processing Toolkit
• Upstream GitHub: ESPnet
• VoiceHub source: VoiceHub model implementation

Configuration

Load configuration without constructing the model:

from voicehub import AutoConfig

config = AutoConfig.for_model('asr_espnet')
print(config.model_type)

Property	Value
Canonical model type	asr_espnet
Configuration class	ESPnetASRConfig
Architecture class	ESPnetASRForSpeechRecognition

Processing

Create the registered processor without allocating model weights:

from voicehub import AutoProcessor

processor = AutoProcessor.from_pretrained(
    'espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best',
    model_type='asr_espnet',
)
print(type(processor).__name__)

Inference

The Usage example returns ASROutput through AutoModelForSpeechRecognition.

Input and output contract

Property	Value
Readiness	integrated-raw
Data architecture	hybrid-ctc-attention
Sample rate	16,000 Hz
Contract getter	get_asr_dataset_spec('asr_espnet')

Variant	Required fields	One of	Boundary	Other rules
raw-audio	—	audio / audio_path; text / transcription / transcript	Source	at most one: audio / audio_path; text / transcription / transcript
espnet-feature-transcript	features	text / transcription / transcript	Prepared	at most one: text / transcription / transcript
espnet-waveform-model-ready	waveforms, waveform_lengths, labels, label_lengths	—	Prepared	—
espnet-feature-model-ready	features, feature_lengths, labels, label_lengths	—	Prepared	—

ESPnet Transformer joint CTC/attention raw and cached records. 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	native
Family	speech-sequence-to-sequence
Recipe	single-phase
Default phase	speech_recognition
Training checkpoint	espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best
Native training graph	yes

Phase	Kind	Components	Required inputs	Loss keys
speech_recognition	objective	model	labels, label_lengths	loss, ctc_loss, attention_loss

The integration accepts its declared source or prepared contract directly. Call model.validate_training_support() first, then follow the training workflow.

Checkpoints, provenance, license, and limitations

Property	Value
Default checkpoint	espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best
Hugging Face ID	espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best Repository availability verified through the Hugging Face model API on 2026-08-11; pin a revision before production use.
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.asr_native.espnet.ESPnetASRForSpeechRecognition
Configuration	voicehub.models.asr_native.configuration.ESPnetASRConfig
Source provenance	voicehub/architectures/espnet_transformer/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

ESPnetASRConfig

View source

ESPnetASRConfig(**config_kwargs)

Parameters

• **config_kwargs — Configuration fields validated by ESPnetASRConfig.

Model

ESPnetASRForSpeechRecognition

View source

AutoModelForSpeechRecognition.from_pretrained(
    pretrained_model_name_or_path,
    *,
    model_type='asr_espnet',
    config=None,
    **model_kwargs,
)

Parameters

• pretrained_model_name_or_path — Hub ID or compatible local directory.
• model_type — Canonical model type; use 'asr_espnet'.
• config — Optional preloaded ESPnetASRConfig instance.
• **model_kwargs — Model-specific loading arguments.

from voicehub import get_model_spec

spec = get_model_spec('asr_espnet')
print(spec.display_name, spec.task.value)

Purpose	Public object
Discover	get_model_spec('asr_espnet')
Load and run	AutoModelForSpeechRecognition
Configure	ESPnetASRConfig
Process	AutoProcessor
Model implementation	ESPnetASRForSpeechRecognition
Normalized output	ASROutput
Training contract	get_training_spec('asr_espnet')
Optimization lifecycle	available_optimization_passes, apply_optimization_plan, optimization_manifest, restore_optimization_plan

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