Skip to page content
SAVRN
Search Plan a project

Independent publisher

Cstr

cstr

Models in Library3
Datasets in Library1
Models on Hugging Face520
Followers119

Compare the published evidence

This profile connects the 4 model and dataset records 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, cc-by-nc-4.0, mit. 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.

Models

Toyama et al.'s hierarchical frequency-time transformer for piano transcription (ISMIR 2023, sony/hFT-Transformer, MIT), converted to GGUF for the ggml runtime in Quantisation is free here, q40 included. That is not the usual result (cosine 0.870), and in this model velocity feeds the decoder's ignorezero gate rather than a note duration — so its errors change which notes survive, not how long they last. Contrast the Onsets & Frames GGUF, where q40 damages the frame head and costs 0.5 points of F1-with-offsets, because that head sets durations. 4.5 MiB reaching 70.7% on solo piano makes this the smallest model in this family that reaches that accuracy. Converted from the pruned ONNX export…

Open weights mit ggml

Model · Speech recognition

raon-speech-9b-GGUF

Cstr

GGUF conversion of the speech-to-text subset of KRAFTON/Raon-Speech-9B for CrispASR (--backend raon-speech, or -m raon-speech to auto-download Q4K). The talker, code predictor, Mimi codec, output adaptor and speaker encoder serve speech output only, so they are not converted. CrispASR reproduces RaonPipeline.stt's front end: - the input is resampled 16k → 24k, as the processor does; - the audio is cut into 8 s chunks, each resampled 24k → 16k (a port of torchaudio's sinc resampler); - each chunk gets its own log-mel (per-chunk max) and is encoded on its own; - the 13 Hz encoder output is truncated to the 12.5 Hz frame grid. The prompt is "Transcribe the audio into text"; --ask "..."…

Open weights cc-by-nc-4.0

Model · Speech recognition

index-echo-2b-GGUF

Cstr

Conversion of IndexTeam/Index-Echo-S2TT-2B for the index-echo backend in CrispASR. Weights have passed the independent CPU/CUDA checks below. The backend is available on CrispASR main, including C ABI loading, companion downloads and a pinned nightly regression. The released model transcribes Chinese and translates each subtitle into English, Japanese or Spanish. CrispASR preserves the three-line generation recipe and returns bilingual cues with timestamps and punctuation. English JFK transcription/English translation also matches the released Python model in the CPU fixtures; this is a port-parity result, not a language-wide accuracy claim. The 9B checkpoint is not included. Both files of…

Open weights apache-2.0 ggml

Datasets