fast-gpu-asr
High-throughput batched ASR for NVIDIA GPUs. Run Zipformer and NVIDIA NeMo Parakeet models through one Python API with TensorRT, custom…
What XERJ indexed
Selected work
“support feature workspaces above 2 GiB and reduce encoder reallocatio…”. 9 files, 240 lines in tests, src/fast_gpu_asr.
Licence
The repository
Checked by a person at the pinned commit.
The XERJ corpus
The author agreed by email on 2026-10-15. Same terms as the repository. Answers name the repo, the commit and the file:line.
in licence reviewnot in the hub yetsuggested use: adapt with attribution
automatic-speech-recognitioncudahpcnvidia-gpuparakeet-tdt-0-6b-v3python3tensorrtzipformer
Example questions
- How does fast-gpu-asr implement automatic-speech-recognition?
- What does src/fast_gpu_asr do in fast-gpu-asr?
- Show the cuda code in fast-gpu-asr.
The prompt
Paste it into your AI agent. It clones SoundsGoodAI/fast-gpu-asr at the pinned commit and indexes it on your machine.
Search the GitHub repository SoundsGoodAI/fast-gpu-asr with XERJ (https://hub.xerj.org/corpus/soundsgoodai--fast-gpu-asr). Run these in a shell, in order, and check each result before the next: 1. xerj --help (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh 2. git clone https://github.com/SoundsGoodAI/fast-gpu-asr fast-gpu-asr && git -C fast-gpu-asr checkout 6d7c43200026ed18f1f48ee48b766edf7aa2246c 3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data 4. xerj autoindex ./fast-gpu-asr --url http://127.0.0.1:9200 --prefix fast-gpu-asr --progress plain 5. xerj autoindex map --url http://127.0.0.1:9200 Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt Licence: Apache-2.0. Keep the copyright notice and credit the authors.
Related
DaniilAPI design and specification corporapantheongpu/pantheonsimnineteendo/jsonyxalinawazcode/passli
Selected work and consent: the XERJ registry.