Model card and licenses for both models

README.md

@@ -2,8 +2,6 @@
 library_name: onnx
 pipeline_tag: automatic-speech-recognition
 license: other
-license_name: openmdw-1.1
-license_link: https://openmdw.ai/license/1-1/
 tags:
 - onnx
 - sherpa-onnx
@@ -13,29 +11,34 @@ tags:
 
 # Streaming speech models, as ONNX
 
-The speech recognition model used by [Rhyme Station](https://github.com/benbaker76/RhymeStation),
-a freestyle rap trainer, to turn the microphone into words as they are spoken. Rhyme Station's
-`tools/fetch_model.sh` and `tools/fetch_model.cmd` download from here.
+The speech recognition models used by [Rhyme Station](https://github.com/benbaker76/RhymeStation),
+a freestyle rap trainer, to turn the microphone into words as they are spoken. The app downloads
+the one it is set to use from here, as do its `tools/fetch_model.sh` and `tools/fetch_model.cmd`.
 
-**Nothing here was trained or converted by this organization.** The files are an unmodified
-copy, kept here so the app has a stable place to download from.
+**Nothing here was trained or converted by this organization.** The files are unmodified copies,
+kept here so the app has a stable place to download from, and each model stays under the
+license its authors gave it: see the file in its folder.
 
-| Folder | Size | Original model | ONNX export |
-| --- | --- | --- | --- |
-| `sherpa-onnx-nemotron-3.5-asr-streaming-0.6b-560ms-int8-2026-06-11` | 682 MB | [nvidia/nemotron-3.5-asr-streaming-0.6b](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) | [csukuangfj2](https://huggingface.co/csukuangfj2/sherpa-onnx-nemotron-3.5-asr-streaming-0.6b-560ms-int8-2026-06-11), for [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx) |
+| Folder | Size | Model | ONNX export | License |
+| --- | --- | --- | --- | --- |
+| `sherpa-onnx-nemotron-3.5-asr-streaming-0.6b-560ms-int8-2026-06-11` | 682 MB | [nvidia/nemotron-3.5-asr-streaming-0.6b](https://huggingface.co/nvidia/nemotron-3.5-asr-streaming-0.6b) | [csukuangfj2](https://huggingface.co/csukuangfj2/sherpa-onnx-nemotron-3.5-asr-streaming-0.6b-560ms-int8-2026-06-11) | [OpenMDW-1.1](https://openmdw.ai/license/1-1/) |
+| `sherpa-onnx-streaming-zipformer-en-kroko-2025-08-06` | 71 MB | [Banafo/Kroko-ASR](https://huggingface.co/Banafo/Kroko-ASR), English community model | [csukuangfj](https://huggingface.co/csukuangfj/sherpa-onnx-streaming-zipformer-en-kroko-2025-08-06) | CC BY-SA |
 
-The folder holds a streaming transducer in the layout sherpa-onnx expects: `encoder.int8.onnx`,
-`decoder.int8.onnx`, `joiner.int8.onnx` and `tokens.txt`. The weights are 8-bit quantized and the
-chunk size is 560 ms. The language is set per stream, for example `en`, `ja` or `auto`.
+Both are streaming transducers in the layout [sherpa-onnx](https://github.com/k2-fsa/sherpa-onnx)
+expects: an encoder, a decoder, a joiner and `tokens.txt`, with 8-bit quantized weights.
+
+- **Nemotron** is the more accurate, most of all on casual speech, and understands many
+  languages (the language is set per stream, for example `en`, `ja` or `auto`). Its chunk size
+  is 560 ms.
+- **Kroko** is English only, a tenth of the size and several times faster, which suits a phone.
 
 | File | SHA-256 |
 | --- | --- |
-| `encoder.int8.onnx` | `012e9321373af99021415e0b0eb3ec827b4be3153be6f30d9b448fe65e896e68` |
-| `decoder.int8.onnx` | `19f9c98fc6d0a2c33a65a43b36fdb2e914c26c0aa9764be3aebc502a1e982fb0` |
-| `joiner.int8.onnx` | `4101c7c679a0bc30483794b27a059e34e79232aa2068d78d51231a22c8b0d7ce` |
-| `tokens.txt` | `729cc103155bafa785f9cd45746cd41cabe97eab7182fc04d594129587958f8a` |
-
-## License
-
-The model is NVIDIA's, released under the [OpenMDW-1.1](https://openmdw.ai/license/1-1/) license.
-A copy is in [LICENSE](LICENSE).
+| `sherpa-onnx-nemotron-…/encoder.int8.onnx` | `012e9321373af99021415e0b0eb3ec827b4be3153be6f30d9b448fe65e896e68` |
+| `sherpa-onnx-nemotron-…/decoder.int8.onnx` | `19f9c98fc6d0a2c33a65a43b36fdb2e914c26c0aa9764be3aebc502a1e982fb0` |
+| `sherpa-onnx-nemotron-…/joiner.int8.onnx` | `4101c7c679a0bc30483794b27a059e34e79232aa2068d78d51231a22c8b0d7ce` |
+| `sherpa-onnx-nemotron-…/tokens.txt` | `729cc103155bafa785f9cd45746cd41cabe97eab7182fc04d594129587958f8a` |
+| `sherpa-onnx-streaming-zipformer-en-kroko-…/encoder.onnx` | `d4881c57449d581e0770fd53fa66c2fdc6cd167d92ece7c715e603defc96d9d4` |
+| `sherpa-onnx-streaming-zipformer-en-kroko-…/decoder.onnx` | `455ba38466fce8d5a57e7db68a323b684079ca4d9e1dd93a740d9b2429aae3b1` |
+| `sherpa-onnx-streaming-zipformer-en-kroko-…/joiner.onnx` | `d406f616736350e2a7df3e39398b78eb2fc1a2ca6973a19d3853fa3227e25b52` |
+| `sherpa-onnx-streaming-zipformer-en-kroko-…/tokens.txt` | `396dbeb5f4858875690716084f54e90d339679d0ba3e6b5b584f3d7589254d2d` |

sherpa-onnx-streaming-zipformer-en-kroko-2025-08-06/LICENSE.md

@@ -0,0 +1,10 @@
+# License
+
+This is the English community streaming model of [Kroko ASR](https://huggingface.co/Banafo/Kroko-ASR)
+by Banafo, in the export published for sherpa-onnx as
+[csukuangfj/sherpa-onnx-streaming-zipformer-en-kroko-2025-08-06](https://huggingface.co/csukuangfj/sherpa-onnx-streaming-zipformer-en-kroko-2025-08-06).
+The files are unmodified.
+
+Banafo releases its community models under the Creative Commons Attribution-ShareAlike
+license (CC BY-SA); see the Kroko ASR page above for their terms. Credit Banafo / Kroko ASR
+when you redistribute these files, and pass them on under the same license.