Skip to content
#

wer

Here are 60 public repositories matching this topic...

Streaming speech recognition toolkit: log-mel features, CTC greedy and prefix-beam decoding, transducer-style frame-synchronous emission, forced alignment, Chinese/English CER-WER metrics, and a chunked streaming pipeline with latency accounting. NumPy core with a CPU-only torch extra; trainable demos on synthetic audio, fully offline.

  • Updated Sep 26, 2026
  • Python

pytest for voice agents — open-source testing and observability for voice AI. Simulate real callers over real audio, measure exact WER against known ground truth, and attribute every failure to STT, LLM, or TTS. Self-hosted, Apache-2.0.

  • Updated Jul 30, 2026
  • Python

Developed a Marathi speech-to-text application using the Hugging Face whisper ASR models. Trained the model with a custom audio dataset and fine-tuned it for optimized performance. Deployed the model on the Hugging Face Model Hub, achieving a WER of 0.74 for the base model.

  • Updated Jan 29, 2024
  • Jupyter Notebook

Add this topic to your repo

To associate your repository with the wer topic, visit your repo's landing page and select "manage topics."

Learn more