Pocket TTS ONNX and Whisper q5, Estonian

README.md

@@ -1,3 +1,61 @@
 ---
 license: cc-by-sa-4.0
+language:
+  - et
+tags:
+  - text-to-speech
+  - automatic-speech-recognition
+  - onnx
+  - whisper.cpp
+  - robotics
 ---
+
+# Go2 dock models
+
+Estonian speech models that Meridein's Unitree Go2 EDU docks run: the
+voice (Pocket TTS) and speech recognition (Whisper). Both are derived from
+public models, converted for the dock's Jetson. A dock downloads them at a
+pinned commit and checks each file's sha256 before using it.
+
+**Files are never overwritten here.** A new version gets a new file name, so
+a release that pins a commit and a sha256 keeps working.
+
+| file | what | size | sha256 |
+|---|---|---|---|
+| `pocket-cpp-et.tar.gz` | Pocket TTS, Estonian, as ONNX for PocketTTS.cpp (one folder, `pocket-cpp-et/`) | 436 064 256 | `1cf3ae8b3eab0724a023a8e5852272e0a870fccbd5fe7bc61a48940a680cd3ca` |
+| `ggml-whisper-large-v3-turbo-et-verbatim-2604-q5_0.bin` | Whisper large-v3-turbo, Estonian, q5_0 for whisper.cpp | 574 041 195 | `ec401581b6ac1788b4eff8b92c5257a65bf24b50be1e488387fd9760166a1ad7` |
+
+## `pocket-cpp-et.tar.gz`: Pocket TTS, Estonian (ONNX)
+
+- **Run by** [PocketTTS.cpp](https://github.com/VolgaGerm/PocketTTS.cpp) at
+  `e801e7d`, with `--precision int8`. The int8 set is what runs; the fp32
+  files are kept beside it.
+- **Made from** [cbentes/pocket-tts-estonian](https://huggingface.co/cbentes/pocket-tts-estonian):
+  the weights and tokenizer at `e8d2fd9cc01ae6e4e505269adcc1d9bdaecbea0f`,
+  the config and the six voice clips at
+  `b37e49dd65514fb79a05cff2ace696e24af15d66`. Exported with pocket-tts
+  2.1.0 and PocketTTS.cpp's `export_onnx.py` at `e801e7d`; the
+  beginning-of-sequence before the voice is in `mimi_encoder.onnx`.
+  `export_info.json` inside records the same.
+- **Licence:** CC BY-SA 4.0, as the weights it is made from, which were
+  trained on the TalTech Estonian Speech Dataset 1.0. Credit:
+  cbentes/pocket-tts-estonian and TalTech. Changes: converted to ONNX and
+  quantised to int8. Share-alike: this derivative is under the same licence.
+
+## `ggml-whisper-large-v3-turbo-et-verbatim-2604-q5_0.bin`: Whisper, Estonian
+
+- **Run by** `whisper-server` ([whisper.cpp](https://github.com/ggml-org/whisper.cpp)),
+  language `et`.
+- **Made from** [TalTechNLP/whisper-large-v3-turbo-et-verbatim-2604](https://huggingface.co/TalTechNLP/whisper-large-v3-turbo-et-verbatim-2604),
+  its ggml model (`ggml/ggml-model.bin`, sha256 `4e231f931f029850d7ca497efe4223f85c495a27d986d955f9a577ac1cd02edb`),
+  quantised to `q5_0` with whisper.cpp's quantize tool (whisper.cpp
+  `60c0be6`). The quantised model needs about 1 GB less memory.
+- **Licence:** that of TalTechNLP's model, which this file is derived from.
+  See their model card; credit: TalTech (Tallinn University of Technology).
+  The repository's `cc-by-sa-4.0` tag is the Pocket model's.
+
+## Checking a download
+
+```bash
+sha256sum -c SHA256SUMS
+```

SHA256SUMS

@@ -0,0 +1,2 @@
+1cf3ae8b3eab0724a023a8e5852272e0a870fccbd5fe7bc61a48940a680cd3ca  pocket-cpp-et.tar.gz
+ec401581b6ac1788b4eff8b92c5257a65bf24b50be1e488387fd9760166a1ad7  ggml-whisper-large-v3-turbo-et-verbatim-2604-q5_0.bin

ggml-whisper-large-v3-turbo-et-verbatim-2604-q5_0.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec401581b6ac1788b4eff8b92c5257a65bf24b50be1e488387fd9760166a1ad7
+size 574041195

pocket-cpp-et.tar.gz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cf3ae8b3eab0724a023a8e5852272e0a870fccbd5fe7bc61a48940a680cd3ca
+size 436064256