Add CrispASR ARK-ASR speech-to-text backend#12006
Merged
Merged
Conversation
ARK-ASR-3B (Whisper-large-v3 encoder + Qwen2.5-3B LM decoder), a new CrispASR backend in v0.8.6. Adds it alongside the other Crisp ASR backends: --backend ark-asr, 19 languages, three GGUF models from cstr/ark-asr-3b-GGUF (q4_k / q8_0 / f16). Requires the CrispASR v0.8.6 engine binary. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
Adds ARK-ASR as a new CrispASR speech-to-text backend (Video → Audio to text → Crisp ASR).
ARK-ASR-3B = Whisper-large-v3 encoder (partial RoPE) + Qwen2.5-3B LM decoder — a new backend in CrispASR v0.8.6.
Details (parallel to the existing Crisp ASR backends, e.g. Granite)
CrispAsrArkbackend:--backend ark-asr, 19 languages (zh, en, de, ja, fr, ko, es, pl, it, ro, hu, cs, nl, fi, hr, sk, sl, et, lt), three GGUF models fromcstr/ark-asr-3b-GGUF(q4_k 3.52 GB / q8_0 4.29 GB / f16 7.51 GB).CrispAsrEnginebackend list;WhisperChoice.CrispAsrArk+CommandLineParameterCrispAsrArksetting;CrispASRARK.txthelp asset.Notes
unknown backend 'ark-asr'). The download URL is already on v0.8.6 (Update CrispASR to v0.8.6 #12003) for fresh installs.Builds clean.
🤖 Generated with Claude Code