SpeechBrain

SpeechBrain

SpeechBrain is an open-source, all-in-one conversational AI platform developed at Mila and Université de Montréal. A single, modular codebase covers automatic speech recognition, speaker recognition and diarisation, speech enhancement and separation, language identification, and spoken language understanding.

Key Features

• 200+ pretrained models on HuggingFace Hub across all speech tasks
• Modular Brain class: compose any pipeline from reusable blocks
• State-of-the-art ASR with Transformer, Conformer, and hybrid CTC/attention
• Speaker verification and identification (ECAPA-TDNN, x-vectors)
• Speech enhancement: MetricGAN+, SEGAN, and ConvTasNet separation

Quick Start

pip install speechbrain

import speechbrain as sb
from speechbrain.inference.ASR import EncoderDecoderASR

asr_model = EncoderDecoderASR.from_hparams(
    source="speechbrain/asr-conformer-transformerlm-librispeech",
    savedir="pretrained_models/asr-transformer-transformerlm-librispeech",
)
result = asr_model.transcribe_file("audio.wav")
print(result)

npx ai-supply add speechbrain-audio-toolkit

Curated mirror of the open-source SpeechBrain (Apache-2.0). Get it from the source.