wavlab-speech/versa

Your faithful, impartial partner for audio evaluation — know yourself, know your rivals. 真实评测，知己知彼。A unified benchmark framework for ASR/TTS/Audio Codec/audio LLM evaluation

PESQ (Perceptual Evaluation of Speech Quality) Wrapper for Python Users (narrow band and wide band)

Unified automatic quality assessment for speech, music, and sound.

Metrics for evaluating music and audio generative models – with a focus on long-form, full-band, and stereo generations.

speech to text benchmark framework

Speed and samples benchmark: for all types of text to speech (TTS) models on Windows/Linux/Mac.

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)