Remove local export path from metadata; add model card

README.md

@@ -0,0 +1,76 @@
+---
+license: apache-2.0
+library_name: pytorch
+tags:
+- forced-alignment
+- word-alignment
+- speech
+- audio
+- gguf
+---
+
+# FuseAlign multilingual (CJK fine-tune, step 2,500)
+
+Word-level forced aligner: given a recording and its transcript, it predicts each word's start and end on a 1 ms
+grid plus a presence probability. A reproduction of FuseAlign ([Vaidya et al., 2026](https://arxiv.org/abs/2609.33650))
+by Zyphra: the multilingual model (100,000 steps), fine-tuned 2,500 steps on CJK junction-corrected labels.
+
+Code, usage, long-form alignment and the C++/ggml CLI:
+[github.com/Zyphra/fusealign-multilingual](https://github.com/Zyphra/fusealign-multilingual).
+
+## Files
+
+| File | Size | Use |
+| --- | ---: | --- |
+| `fusealign-multilingual-cjkft-step2500.safetensors` | 1.34 GB | PyTorch package (`torch.hub`, `fusealign_hub`): FuseAlign fp32, Dia text encoder bf16 |
+| `fusealign-multilingual-cjkft-step2500-f32.gguf` | 1.35 GB | ggml port: FuseAlign F32, Dia BF16, Silero VAD F32 |
+| `fusealign-multilingual-cjkft-step2500-q8_0.gguf` | 0.51 GB | ggml port: transformer matmuls Q8_0, other Dia tensors BF16, the rest F32 |
+
+## Usage
+
+```python
+import soundfile as sf
+import torch
+
+aligner = torch.hub.load("Zyphra/fusealign-multilingual", "fusealign", trust_repo=True, device="cuda")
+wav, sr = sf.read("speech.wav", dtype="float32")
+words = aligner.align(torch.from_numpy(wav), sr, "the transcript of the recording")
+# [WordAlignment(word='the', start=..., end=..., presence=..., placed=True), ...]
+```
+
+## Evaluation
+
+% of word boundaries off by more than 50 ms (the paper's asymmetric error):
+
+| Corpus | % >50 |
+| --- | ---: |
+| TIMIT | 16.55 |
+| Buckeye | 24.58 |
+| AMI-silver | 49.38 |
+| TIMIT-long | 17.25 |
+| BZNSYP Mandarin (gold) | 15.94 |
+| FLEURS Mandarin | 17.95 |
+| FLEURS Japanese | 14.02 |
+| FLEURS Korean | 8.39 |
+| FLEURS Spanish | 19.66 |
+| FLEURS Portuguese | 9.30 |
+| FLEURS French | 13.15 |
+| FLEURS German | 13.29 |
+| FLEURS Russian | 12.74 |
+
+## License
+
+Apache-2.0. The checkpoint and GGUFs include the Dia text encoder weights from
+[nari-labs/Dia-1.6B-0626](https://huggingface.co/nari-labs/Dia-1.6B-0626) (Apache-2.0); the GGUFs include
+[Silero VAD](https://github.com/snakers4/silero-vad) weights (MIT).
+
+## Citation
+
+```bibtex
+@article{vaidya2026fusealign,
+  title   = {FuseAlign: Forced Alignment in the Wild},
+  author  = {Vaidya, Mithilesh and Bailey, Stephen and Badam, Sumukh and Bendel, Matthew and He, Xingzhe},
+  journal = {arXiv preprint arXiv:2609.33650},
+  year    = {2026}
+}
+```

fusealign-multilingual-cjkft-step2500-f32.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01b2e27c2a3e404f3ea9442fd94a5494423501a09a7eead62c3d3d8741b25ea
-size 1345210592
+oid sha256:a54a49f309c96dd5ff92876986bc9875ac32227794161a79337422af9781ee9b
+size 1345210432

fusealign-multilingual-cjkft-step2500-q8_0.gguf

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3fa988089e78697af1be1050727aaf040e2ca8f9858e283de318df3e7945cbe
-size 514803936
+oid sha256:183b4247afe5de7c0d163eea4a41057fa8dd0da27f6a898632b1aba53db77a3f
+size 514803776

fusealign-multilingual-cjkft-step2500.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad29a3533eaa7e593df19673f772ed5a67d81bd849113fb6d47b124f433da18
-size 1343979116
+oid sha256:1c8c4243e1362453d7e8277da3b39480ea1c45507b87e5dfa7f496fade5d72c6
+size 1343979004