Update README.md

README.md

@@ -1,6 +1,7 @@
 ---
 license: other
 library_name: nemo-speech.cpp
+base_model: nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B
 tags:
 - asr
 - gguf
@@ -12,7 +13,14 @@ tags:
 ---
 # nemo-speech (CUDA build for Tesla T4)
 
-Prebuilt `nemo-speech` server from NeMo-Speech.cpp, so Kaggle/Colab notebooks can skip the ~40 min compile.
+Prebuilt `nemo-speech` server from NeMo-Speech.cpp, so Kaggle/Colab notebooks can skip the ~40 min compile. It runs [NVIDIA Nemotron-3.5-Transcribe-30B-A4B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B) (speech recognition) from the GGUF conversion [AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF](https://huggingface.co/AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF). This repo contains the binary only, not the model weights.
+
+## Parent model
+| | |
+|---|---|
+| Original model | [nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B](https://huggingface.co/nvidia/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B) |
+| GGUF weights used | [AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF](https://huggingface.co/AtomicChat/NVIDIA-Nemotron-3.5-Transcribe-30B-A4B-GGUF) |
+| Inference engine | NeMo-Speech.cpp (ggml / llama.cpp based) |
 
 ## Build
 | | |
@@ -32,9 +40,9 @@ os.chmod("/tmp/nemo-bin/bin/nemo-speech", 0o755)
 # libraries sit next to the binary
 os.environ["LD_LIBRARY_PATH"] = "/tmp/nemo-bin/bin:" + os.environ.get("LD_LIBRARY_PATH", "")
 ```
-Then run `/tmp/nemo-bin/bin/nemo-speech serve --asr-model <model.gguf> ...`.
+Then run `/tmp/nemo-bin/bin/nemo-speech serve --asr-model <model.gguf> ...`, with the GGUF files downloaded from the repo above.
 
 ## Limits
 - Compiled for compute capability 7.5 only. It will not run on other GPUs (A100, L4, P100).
 - Needs an NVIDIA driver with `libcuda.so.1` and a glibc/libstdc++ at least as new as the build machine's (see `ldd.txt`).
-- Licence: follows the NeMo-Speech.cpp, ggml and CUDA licences; check them before redistributing.
+- Licence: the model is under NVIDIA's own licence (see the parent model page); the binary follows the NeMo-Speech.cpp, ggml and CUDA licences. Check them before redistributing.