whisper-tiny-mic

Slim model weights, executable usage and framework expectations in one repository.

• Contract manifest
• Transformers usage
• Transformers expectations
• Fixture provenance

Contract

MIC: Whisper speech recognition

Model integration contract (MIC) for one usage path, across the checkpoints that share it. This repository holds the contract code and the manifest; each framework keeps its own expected results and pins this repository by revision. The model repositories are unchanged. It is a test artifact, not a model: exclude it from model search.

Usage path: WhisperProcessor + WhisperForConditionalGeneration.generate, English transcription, batched.

File	What it is
integration.json	Manifest: checkpoints, which fixture covers each, frameworks, entry points, variants, unsupported targets, comparison rules
integrations/transformers/usage.md	Transformers contract, written as doc-builder runnable markdown: the same blocks are documentation and test

Checkpoint	Slim fixture (every framework PR)
openai/whisper-tiny	hf-internal-testing/mic-whisper-tiny-slim

Checked outputs: generated_tokens, generated_text, label_logprobs, timestamped_tokens, timestamped_text, feature_extractor_config_keys, max_length_tokens, assisted_tokens, longform_tokens, continued_longform_tokens, training.loss, training.gradients, training.updated.

A fixture pass and a real-checkpoint pass have different scopes; either establishes agreement on fixed inputs and a recorded runtime, not correctness on arbitrary inputs.

Slim model

Slim fixture: proto-whisper-tiny-slim

A 3.6M-parameter fixture for the Whisper MIC, covering openai/whisper-tiny. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key 71360928908b. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• Same architecture, smaller config: WhisperForConditionalGeneration, shrunk by the generic rule in sweep.py (encoder_layers 2, decoder_layers 2).
• Processor files copied byte for byte from openai/whisper-tiny: added_tokens.json, generation_config.json, merges.txt, normalizer.json, preprocessor_config.json, special_tokens_map.json, tokenizer.json, tokenizer_config.json, vocab.json.
• Overfit to the contract's training step (200 steps). Random weights failed the input-sensitivity gate: input_features:reverse moved the logits by only 8.6e-05 (threshold 0.001).
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Finite in float32, bfloat16, and float16 (forward, loss, gradients).

Built by build_fixtures.py; build.json records the pinned sources, gate results, and file hashes. This repository includes the slim weights, usage and framework expectations; rebuild the other files with python example/build_fixtures.py --fixture proto-whisper-tiny-slim.