Downloads · 30 days
0
tatsu020/rs35kh-fa-onnx
rs35kh-fa-onnx is a automatic speech recognition model from tatsu020. Use it when you need speech turned into text. It is set up for onnxruntime. The card lists the license as apache-2.0.
This repository hosts an ONNX derivative of reazon-research/japanese-wav2vec2-base-rs35kh for UtaLog's local Japanese lyrics timing module.
Downloads · 30 days
0
Access
Public
Updated Aug 31, 2026
Repo size
203 MB
Likes
0
Public
Click a slice to open those files.
.onnx203 MB · 100%
From the Hugging Face model README
This repository hosts an ONNX derivative of
reazon-research/japanese-wav2vec2-base-rs35kh
for UtaLog's local Japanese lyrics timing module.
It is not an official ReazonSpeech release and is not endorsed by the upstream authors.
rs35kh_ctc_fp16.onnx203351696 bytes5c6b2b5f14445e1dd12cfc055e96bbc47dd87d4e874e43636d212bc201280d48input_values, float32, shape [batch, samples], 16 kHz mono audiologits, shape [batch, frames, 3003]reazon-research/japanese-wav2vec2-base-rs35kh46afc596052b612293c8db256b3a69447a2f57dctools/alignment/convert_rs35kh_to_onnx.py in UtaLogWav2Vec2ForCTC to ONNX, keep the convolutional feature extractor in FP32, convert the encoder suffix to FP16, and normalize Reshape.allowzero for DirectML compatibility.The exact hosted bytes are a recovered development artifact. A later clean conversion passed model validation but was not byte-identical, so this repository does not claim byte-for-byte reproducibility. UtaLog pins this repository's immutable Hub commit and verifies both byte size and SHA-256 before use.
This graph supplies CTC acoustic emissions for alignment against user-provided Japanese lyrics. It is not sufficient by itself to produce an LRC file: UtaLog generates readings, tokenizes the known lyrics, searches monotonic candidates, preserves locked ranges, and exposes low-confidence or unmatched lines for review.
The upstream model card reports poor long-form ASR transcription results. UtaLog therefore uses bounded audio chunks and local-anchor/section alignment rather than decoding a whole song as unrestricted ASR.
The upstream model is distributed under Apache-2.0. This converted derivative is distributed under the same license. See LICENSE-2.0.txt and UtaLog's apps/desktop/resources/alignment/THIRD_PARTY_NOTICES.md for attribution and change information.