Repository navigation
Space on ZeroGPU; publish granite-qwen-500-3 as mazesmazes/tiny-audio - #173
Merged
Merged
Conversation
Space - Runs the model in-process on ZeroGPU instead of calling the RunPod `ta serve` pod. app.py already had the @spaces.GPU path; requirements get the model's dependencies back, and the README front matter gets suggested_hardware: zero-a10g and preload_from_hub for every model the pipeline loads. - `ta deploy` without --endpoint-url now clears a leftover ENDPOINT_URL variable (it would keep the app calling the server) and requests zero-a10g hardware. --endpoint-url still moves the Space to CPU and a `ta serve` server. - librosa added to the Space and Hub requirements: Nemotron's streaming feature extractor imports it, so diarization failed without it. - merge_lora folds a LoRA decoder's adapters into its weights at load (20.6 -> 36.7 tok/s on a Mac, see merge_lora_adapters). A no-op for the new fully fine-tuned model; kept for LoRA models via MODEL_ID. Model card - mazesmazes/tiny-audio main is now tiny-audio-granite-qwen-500-3@989df838 (Granite Speech 5.0 470M NC encoder + fully fine-tuned Qwen3-0.6B, step 16,159), with config.json's model_dtype set to bfloat16 to match how evals run it. Previous model tagged granite-qwen-frozen-4. - License is CC BY-NC-SA 4.0, inherited from the -nc encoder; the card points to granite-qwen-frozen-4 (MIT) for commercial use. - No benchmark table yet: there is no n=1000 eval of this model. Co-Authored-By: Claude Opus 5.5 <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Space: ZeroGPU instead of RunPod
demo/app.pyalready had the@spaces.GPUpath, so this PR adds the model's dependencies back todemo/requirements.txtand putssuggested_hardware: zero-a10gpluspreload_from_hub(every model the pipeline loads) in the Space README.ta deploywithout--endpoint-urlnow deletes any leftoverENDPOINT_URLvariable (otherwise the app keeps calling the server) and requestszero-a10g.--endpoint-urlstill works as before: CPU hardware plus ata serveserver.librosato the Space and Hub requirements. Nemotron's streaming feature extractor imports it, so diarization failed without it.merge_lora, which folds LoRA adapters into the decoder weights at load (20.6 → 36.7 tok/s on a Mac). It does nothing for the new fully fine-tuned model; it's there for LoRA models set viaMODEL_ID.Model card: granite-qwen-500-3 is now
mazesmazes/tiny-audiomain(already published, commit26ce2edf) is a copy oftiny-audio-granite-qwen-500-3@989df838: the Granite Speech 5.0 470M NC encoder plus a fully fine-tuned Qwen3-0.6B, at step 16,159.config.jsonhasmodel_dtypeset tobfloat16to match how evals run it. The previous model is taggedgranite-qwen-frozen-4.-ncencoder. The card points togranite-qwen-frozen-4(MIT) for commercial use.After merge
Test plan
ta dev checkandta dev testpass (1592 passed); the precommit gate passedpipeline("mazesmazes/tiny-audio", trust_remote_code=True)load from the Hub runs in bf16 and transcribes the LibriSpeech and earnings-call demo examples correctly🤖 Generated with Claude Code