speech_t5-mic

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

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

Contract

SpeechT5-ASR

Runnable usage and the framework expectations directory are linked above.

Slim model

Slim fixture: mic-speech_t5-slim

A 4.4M-parameter fixture for the speech_t5 MIC, covering microsoft/speecht5_asr. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.

• Fixture key e46995639189. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking.
• Same architecture, smaller config: SpeechT5ForSpeechToText, shrunk by the generic rule in sweep.py (encoder_layers 2, decoder_layers 2).
• Processor files copied byte for byte from microsoft/speecht5_asr: added_tokens.json, generation_config.json, preprocessor_config.json, special_tokens_map.json, spm_char.model, tokenizer_config.json.
• Random weights (seed 17). They passed the input-sensitivity gate: every perturbation of the contract's inputs moved the logits by at least 0.001 (weakest: input_values:roll_batch, 0.00371), so no training was needed.
• Same tensor names as the real checkpoint. The real checkpoint has every parameter, and so does the fixture.
• Saved in float32, the dtype microsoft/speecht5_asr 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-speech_t5-slim.