Armenian SpeechT5 — ONNX export (TTS_NB_ONNX)
ONNX export of the SpeechT5 encoder/decoder for faster or edge inference (ONNXRuntime, mobile, C++). Pair with HiFi-GAN vocoder separately.
Files
| File | Role |
|---|---|
encoder_model.onnx |
Text → hidden states |
decoder_model.onnx |
Autoregressive mel decoder |
decoder_with_past_model.onnx |
Decoder with KV cache |
decoder_postnet_and_vocoder.onnx |
Postnet (vocoder may still be separate) |
spm_char.model |
SentencePiece tokenizer |
config.json / preprocessor_config.json |
Model config |
When to use
- ONNXRuntime deployment
- Environments without full PyTorch stack
- Latency-sensitive inference pipelines
For PyTorch + Hugging Face, prefer Edmon02/speecht5_finetuned_voxpopuli_hy or Edmon02/TTS_NB_2.
Source checkpoint
Exported from Edmon02/TTS_NB_2 (verify export date in commit history).
Limitations
- ONNX export may not cover full HF
generate_speechAPI — validate your runtime graph - Speaker embeddings must be supplied consistently with training
- Re-export when
TTS_NB_2architecture or opset changes
License
MIT