deploy/parakeet-stt: add edge-stt take-home (3-mode CLI + harness + results)#5
Merged
Conversation
…arness + results) Edge AI STT assessment under edge-stt/: one ./transcribe CLI over three modes (A offline parakeet.cpp, B streaming Zipformer, C multilingual LID), the WER/RTF/memory harness, locked deps, and measured LibriSpeech-300 results. Primary engine parakeet.cpp (tdt=q5_k 1.808%/61x, ctc=q8_0 2.383%/107x, +450MB); sherpa-onnx for Modes B/C and the reproducible alternative. Does not touch the production STT-server deploy files.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds the Edge AI STT assessment under
deploy/parakeet-stt/edge-stt/— additive; the existing production STT-server deploy files (README, genie-parakeet.service, parakeet-stt-server.py, serve-mode.patch) are untouched.Contents (
edge-stt/):./transcribeCLI over three modes — A offline (parakeet.cpp ggml CUDA), B true-streaming (sherpa-onnx Zipformer), C multilingual (Whisper-tiny LID + Parakeet-v3).requirements.lock), and measured LibriSpeech-300 results.Audio payloads / models are gitignored (regenerated by
scripts/get-data.sh+scripts/get-models.sh).