wehub-resource-sync
ba4be087d5
Create PR to main with cherry-pick from release / cherry-pick (push) Failing after 0s
CICD NeMo / pre-flight (push) Failing after 0s
CICD NeMo / configure (push) Has been skipped
Build, validate, and release Neural Modules / pre-flight (push) Failing after 1s
CICD NeMo / code-linting (push) Has been skipped
Build, validate, and release Neural Modules / release (push) Has been skipped
Build, validate, and release Neural Modules / release-summary (push) Has been cancelled
CICD NeMo / cicd-test-container-build (push) Has been cancelled
CICD NeMo / cicd-import-tests (push) Has been cancelled
CICD NeMo / L0_Setup_Test_Data_And_Models (push) Has been cancelled
CICD NeMo / cicd-main-unit-tests (push) Has been cancelled
CICD NeMo / cicd-main-speech (push) Has been cancelled
CICD NeMo / Nemo_CICD_Test (push) Has been cancelled
CICD NeMo / Coverage (e2e) (push) Has been cancelled
CICD NeMo / Coverage (unit-test) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
CICD NeMo / cicd-wait-in-queue (push) Has been cancelled
Universal Streaming Inference
The asr_streaming_infer.py script enables streaming inference for both buffered (CTC/RNNT/TDT) and cache-aware (CTC/RNNT) ASR models. It supports processing a single audio file, a directory of audio files, or a manifest file.
Beyond streaming ASR, the script also supports:
- Inverse Text Normalization (ITN)
- End-of-Utterance (EoU) Detection
- Streaming Speech Translation (requires vLLM installation)
- Word-level and Segment-level Output
All related configurations can be found in the ../conf/asr_streaming_inference/ directory.