s2t-small-librispeech-asr-mic
Slim model weights, executable usage and framework expectations in one repository.
- Contract manifest
- Transformers usage
- Transformers expectations
- Fixture provenance
- How the fixture was shrunk
Contract
Speech2Text speech recognition
Runnable usage and the framework expectations directory are linked above.
Slim model
Slim fixture: s2t-small-librispeech-asr-mic
A 1.5M-parameter fixture for the Speech2Text MIC, covering facebook/s2t-small-librispeech-asr. It is a test artifact, not a usable model, tagged test-artifact to keep it out of candidate-model search.
- Fixture key
f136992f6f3d. It covers every checkpoint whose processor files are byte-identical and whose config matches after shrinking. - Same architecture, smaller config:
Speech2TextForConditionalGeneration, shrunk by the generic rule insweep.py(encoder_layers 2, decoder_layers 2). - Processor files copied byte for byte from
facebook/s2t-small-librispeech-asr:generation_config.json,preprocessor_config.json,sentencepiece.bpe.model,special_tokens_map.json,tokenizer_config.json,vocab.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_features:roll_batch, 0.00613), 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
facebook/s2t-small-librispeech-asrloads 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 s2t-small-librispeech-asr-mic.
- Downloads last month
- 954
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support
Model tree for huggingface-mic/s2t-small-librispeech-asr-mic
Base model
facebook/s2t-small-librispeech-asr