Update model from training (2025-11-15 06:39:44) - Language: cy

MODEL_CARD.md

@@ -4,12 +4,14 @@ This is a Welsh (Cymraeg) text-to-speech model trained using Piper.
 
 ## Model Details
 
-- **Language:** Welsh (cy)
+- **Language:** Welsh (cy) - Monolingual
 - **Sample Rate:** 22,050 Hz
 - **Quality:** Medium
 - **Framework:** Piper/VITS
 - **Model Type:** Single-speaker TTS
-- **Training Dataset:** [techiaith/bu-tts-cy-en](https://huggingface.co/datasets/techiaith/bu-tts-cy-en)
+- **Training Dataset:** [techiaith/bu-tts-cy-en](https://huggingface.co/datasets/techiaith/bu-tts-cy-en) (Welsh samples only)
+
+This model was trained exclusively on Welsh language data from the techiaith/bu-tts-cy-en dataset.
 
 ## Usage
 
@@ -19,11 +21,11 @@ Install [Piper](https://github.com/rhasspy/piper) and use the model:
 
 ```bash
 # Download the model files
-wget https://huggingface.co/techiaith/cy_GB-bu_tts/resolve/main/cy_GB-bu_tts.onnx
-wget https://huggingface.co/techiaith/cy_GB-bu_tts/resolve/main/cy_GB-bu_tts.onnx.json
+wget https://huggingface.co/techiaith/cy_GB-bu_tts/resolve/main/cy_GB-bu_tts-medium.onnx
+wget https://huggingface.co/techiaith/cy_GB-bu_tts/resolve/main/cy_GB-bu_tts-medium.onnx.json
 
 # Generate speech
-echo "Helo, sut ydych chi heddiw?" | piper --model cy_GB-bu_tts.onnx --output_file output.wav
+echo "Helo, sut ydych chi heddiw?" | piper --model cy_GB-bu_tts-medium.onnx --output_file output.wav
 ```
 
 ### Sample Sentences
@@ -34,6 +36,7 @@ Try these example sentences in Welsh:
 - "Diolch yn fawr am eich help."
 - "Mae'r tywydd yn hyfryd heddiw."
 - "Rwy'n dysgu siarad Cymraeg."
+- "Croeso i Gymru!"
 
 ## Training Information
 
@@ -46,6 +49,7 @@ Try these example sentences in Welsh:
   - Checkpoint frequency: Every 5 epochs
   - Gradient clipping: 1.0
   - Warmup epochs: 5
+  - Language filter: Welsh (cy) only
 
 ## License
 
@@ -56,10 +60,10 @@ MIT License - See the training repository for details.
 If you use this model, please cite:
 
 ```bibtex
-@misc{cy_GB-bu_tts,
+@misc{cy_GB_bu_tts,
   title={Welsh Text-to-Speech Model},
   author={Uned Technolegau Iaith, Prifysgol Bangor},
-  year={2024},
+  year={2025},
   publisher={HuggingFace},
   howpublished={\url{https://huggingface.co/techiaith/cy_GB-bu_tts}}
 }