whisper-mic

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

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

Contract

whisper model integration contract

Public Transformers usage validated on a slim fixture on an NVIDIA A10G, with default, eager and bfloat16 variants and fresh-process baseline recording. This prototype declares fixture-only targets; full checkpoint coverage is separate.

Regeneration evidence.

Slim model

Slim fixture: mic-whisper-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 (220 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.
• Saved in float32, the dtype openai/whisper-tiny loads in by default.
• 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 mic-whisper-slim.