ESPnet

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.