Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+license: mit
+language:
+  - km
+tags:
+  - text-to-speech
+  - tts
+  - khmer
+---
+
+# SimpleKhmerTTS
+
+Decoder-only transformer TTS, using [WavTokenizer](https://github.com/jishengpeng/WavTokenizer) as the audio codec and [DDD-Cambodia/khmer-speech-dataset](https://huggingface.co/datasets/DDD-Cambodia/khmer-speech-dataset) as dataset.
+
+## Samples
+
+| Text     | Audio                                                                                                                      |
+| -------- | -------------------------------------------------------------------------------------------------------------------------- |
+| Sample 1 | <audio controls src="https://huggingface.co/AnotherPotatoCoder/Khmer-TTS/resolve/main/sample_audios/sample_1.wav"></audio> |
+| Sample 2 | <audio controls src="https://huggingface.co/AnotherPotatoCoder/Khmer-TTS/resolve/main/sample_audios/sample_2.wav"></audio> |
+| Sample 3 | <audio controls src="https://huggingface.co/AnotherPotatoCoder/Khmer-TTS/resolve/main/sample_audios/sample_3.wav"></audio> |
+| Sample 4 | <audio controls src="https://huggingface.co/AnotherPotatoCoder/Khmer-TTS/resolve/main/sample_audios/sample_4.wav"></audio> |
+
+## Setup
+
+```bash
+git clone https://github.com/FirstPotatoCoder/SimpleKhmerTTS.git
+cd SimpleKhmerTTS
+pip install -q -r requirements.txt
+python scripts/download_weights.py
+```
+
+## Run
+
+```bash
+python examples/run_inference.py " ភាសាខ្មែរមានអក្សរច្រើន ហើយពិបាកសរសេរបន្តិច។ ភាសានេះមានប្រវត្តិយូរអង្វែង និងជាផ្នែកមួយយ៉ាងសំខាន់នៃវប្បធម៌កម្ពុជា។" --speaker_id 0
+```
+
+Or from Python:
+
+```python
+from tts.inference import TTSPipeline
+
+pipe = TTSPipeline(
+    tts_weights="weights/tts.pt",
+    wavtokenizer_weights="weights/wavtokenizer.ckpt",
+    wavtokenizer_config="configs/wavtokenizer_config.yaml"
+)
+
+pipe.generate(" ភាសាខ្មែរមានអក្សរច្រើន ហើយពិបាកសរសេរបន្តិច។", speaker_id=1, out_path="out.wav")
+```
+
+## Limitations
+
+- The model sometimes hallucinates, generating babbling or garbled output on rare or unseen words, making it ill-suited for direct deployment — likely due to the limited amount of training data and codec's limited performance on Khmer audio.
+- Works best when generating ~3s to 10s of audio, matching the length distribution of its training data.
+- No chunking support yet — the current repo only supports clip-by-clip generation, one sample at a time.
+
+## Credits
+
+- Data: [Khmer Speech Dataset](https://huggingface.co/datasets/DDD-Cambodia/khmer-speech-dataset) by DDD-Cambodia
+
+- Compute: [Kaggle](https://www.kaggle.com) for free T4 GPU access
+
+- Audio tokenizer/codec: [WavTokenizer](https://github.com/jishengpeng/WavTokenizer)
+  (vendored under `wavtokenizer/`, trimmed to inference-only code).