A frozen embedding encoder. A 9.66M trainable reader. Speech transcription without encoder fine-tuning. Embed2ASR reuses the representations of an audio embedding model for speech recognition. The audio tower of Google's EmbeddingGemma 2 stays frozen and unmodified. We take its pre-pooling lasthiddenstate (1536-d temporal features, 25 frames per second; not the final pooled embedding vector) and decode it with a GRU-CTC reader of 9,655,172 trainable parameters. About 314.5M parameters are loaded for inference (304,824,608 frozen encoder + 9,655,172 reader). Languages: Taiwanese Mandarin, English and Mandarin-English code-switching. This is representation reuse, not a new ASR backbone…
Independent publisher
Oliver Yu
tc3oliver
Models in Library1
Datasets in Library0
Models on Hugging Face4
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Speech recognition.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.