Add NeMo-Speech.cpp GGUF and tokenizer assets

.gitattributes

@@ -46,3 +46,4 @@ Feb26_CE-Removed_Magpie-TTS-5speakers.nemo filter=lfs diff=lfs merge=lfs -text
 magpie_tts_next.nemo filter=lfs diff=lfs merge=lfs -text
 CE-Removed_Magpie-TTS-ML-V1_5speakers_new_withinferenceparams.nemo filter=lfs diff=lfs merge=lfs -text
 magpie_tts_next_withoutinferenceparams.nemo filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -158,7 +158,7 @@ This model is not intended for zero-shot voice cloning, languages outside the 12
 ## How to Get Started with the Model
 
 > [!TIP]
-> Choose a path below: [Hosted API Quickstart](#hosted-api-quickstart) (no GPU required) or [Local Inference with NeMo Speech](#local-inference-with-nemo) (Method 1 for a single utterance, Method 2 for batch evaluation).
+> Try the [hosted API](#hosted-api-quickstart), run locally with [NeMo-Speech.cpp](#run-magpietts-locally-with-nemo-speechcpp), or use the [NeMo Speech Framework](#local-inference-with-nemo) for Python inference and training.
 
 ### Hosted API Quickstart
 
@@ -234,7 +234,38 @@ python python-clients/scripts/tts/talk.py \
 
 > **Note:** Voice IDs and supported sample rates follow the deployed NIM. Use `--list-voices` against this endpoint, or see the **API Reference** on the [Magpie TTS Multilingual](https://build.nvidia.com/nvidia/magpie-tts-multilingual) page.
 
-### Local Inference with NeMo Speech
+### Run MagpieTTS locally with NeMo-Speech.cpp
+
+[NeMo-Speech.cpp](https://github.com/NVIDIA/NeMo-Speech.cpp) provides a
+lightweight native C++ runtime for running this model locally. This `v2602`
+GGUF uses the tokenizer assets contained in the original `.nemo` archive and
+the companion NanoCodec decoder.
+
+After [installing NeMo-Speech.cpp](https://github.com/NVIDIA/NeMo-Speech.cpp#installation):
+
+```bash
+hf download nvidia/magpie_tts_multilingual_357m \
+  --include magpie_tts_multilingual_357m.v2602.f16.gguf \
+  --include magpie_tts_multilingual_357m.nemo \
+  --local-dir magpie-tts
+
+mkdir -p magpie-tts/extracted
+tar -xf magpie-tts/magpie_tts_multilingual_357m.nemo \
+  -C magpie-tts/extracted
+
+hf download nvidia/nemo-nano-codec-22khz-1.89kbps-21.5fps \
+  nemo_nano_codec_22khz_1.89kbps_21.5fps.decoder.f16.gguf \
+  --local-dir nano-codec
+
+nemo-speech synthesize "Hello from Magpie Multilingual." \
+  --magpie-model magpie-tts/magpie_tts_multilingual_357m.v2602.f16.gguf \
+  --codec-model nano-codec/nemo_nano_codec_22khz_1.89kbps_21.5fps.decoder.f16.gguf \
+  --tokenizer-dir magpie-tts/extracted \
+  --language en-US \
+  --output speech.wav
+```
+
+### Python Inference with the NeMo Speech Framework
 
 <a id="local-inference-with-nemo"></a>
 

magpie_tts_multilingual_357m.v2602.f16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901d299a8b1df016cf81cae0089a7a7c15627b9633d033357e15a47d9a219a75
+size 448604832