Transfer from cxlrd/luganda-tts-v3

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+luganda_fastpitch.nemo filter=lfs diff=lfs merge=lfs -text
+luganda_hifigan.nemo filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,34 @@
+---
+language: lg
+license: apache-2.0
+tags: [text-to-speech, tts, nemo, luganda, african-languages]
+datasets: [Sunbird/salt]
+---
+
+# Luganda TTS v3
+
+Text-to-Speech system for Luganda using NVIDIA NeMo.
+
+## Models
+| Model | Description | Size |
+|-------|-------------|------|
+| `luganda_fastpitch.nemo` | FastPitch spectrogram generator | 187 MB |
+| `luganda_hifigan.nemo` | HiFi-GAN neural vocoder | 339 MB |
+
+## Training
+- **Dataset**: Sunbird/salt (~2,380 samples, 2.69 hours)
+- **FastPitch**: 20,000 steps
+- **HiFi-GAN**: 20,000 steps
+- **Sample Rate**: 22,050 Hz
+
+## Usage
+```python
+from nemo.collections.tts.models import FastPitchModel, HifiGanModel
+
+fastpitch = FastPitchModel.restore_from("luganda_fastpitch.nemo")
+hifigan = HifiGanModel.restore_from("luganda_hifigan.nemo")
+
+text = "Oli otya?"
+spec = fastpitch.generate_spectrogram(tokens=fastpitch.parse(text))
+audio = hifigan.convert_spectrogram_to_audio(spec=spec)
+```

luganda_fastpitch.nemo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eddc12da7d377bb3bf1dc0dc3a761dc86a0f4bdd153577faf528c1d1e23d759
+size 187023360

luganda_hifigan.nemo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9d19d517bcb3042fe3c776fe151894f98e3ae96825f1d14b0c62b81a69e0681
+size 339210240