ESPnet
End-to-end speech processing toolkit covering ASR, TTS, speech translation, enhancement, and speaker diarisation.
ESPnet
ESPnet is an end-to-end speech processing toolkit jointly developed by Johns Hopkins University, Carnegie Mellon University, and the broader academic community. It provides a complete training-and-inference pipeline for automatic speech recognition (ASR), text-to-speech (TTS), speech translation (ST), speech enhancement (SE), and speaker diarisation.
Key Features
- State-of-the-art ASR with Transformer, Conformer, and Whisper-based architectures
- Multilingual and code-switching support across 30+ languages
- Full pipeline: data preparation → feature extraction → training → decoding
- Pre-trained models on Hugging Face Hub via
espnet_model_zoo - Speech2Speech and cascaded/end-to-end speech translation
Quick Start
pip install espnet espnet_model_zoo
from espnet2.bin.asr_inference import Speech2Text
speech2text = Speech2Text.from_pretrained(
"espnet/kan-bayashi_ljspeech_vits"
)
import soundfile as sf
speech, rate = sf.read("speech.wav")
result = speech2text(speech)
print(result[0][0]) # recognised text
npx ai-supply add espnet-speech-processing
Curated mirror of the open-source ESPnet (Apache-2.0). Get it from the source.
Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.
Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).
The same gate an agent runs before installing (POST /api/v1/trust/espnet-speech-processing/check). Click a policy:
Consume ESPnet programmatically. Authenticate with an API key or session — see Authorize an agent.
# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/espnet-speech-processing
# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/espnet-speech-processing/check \
-H "Content-Type: application/json" \
-d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'
# CLI
npx ai-supply add espnet-speech-processing
# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/espnet-speech-processing/install \
-H "Authorization: Bearer $AIM_KEY"
# MCP tool
install_listing({ "slug": "espnet-speech-processing" })OpenAPI spec →Curated mirror — latest upstream source. See the repository for tagged releases.