DeutscheKI/tevr-asr-tool
A 284-line C++ CLI tool performing state-of-the-art German speech-to-text using wav2vec2 acoustic models and KenLM language models.
Not currently ranked — collecting fresh signals.
star history
This tool provides offline, private German speech recognition by running a pre-trained wav2vec2-xls-r-1b acoustic model with a KenLM language model for beam search re-scoring. Users pass a WAV file to the CLI and receive transcribed text. The acoustic model is sourced from HuggingFace transformers, while the language model handles token logits to text conversion and scoring.
Frequently asked
- What is DeutscheKI/tevr-asr-tool?
- A 284-line C++ CLI tool performing state-of-the-art German speech-to-text using wav2vec2 acoustic models and KenLM language models.
- Is tevr-asr-tool open source?
- Yes — DeutscheKI/tevr-asr-tool is open source, released under the MIT license.
- What language is tevr-asr-tool written in?
- DeutscheKI/tevr-asr-tool is primarily written in C.
- How popular is tevr-asr-tool?
- DeutscheKI/tevr-asr-tool has 410 stars on GitHub.
- Where can I find tevr-asr-tool?
- DeutscheKI/tevr-asr-tool is on GitHub at https://github.com/DeutscheKI/tevr-asr-tool.