Downloads · 30 days
9
14% of all-time downloads
TTS_NB_ONNX
Edmon02/TTS_NB_ONNX
TTS_NB_ONNX is a text-to-speech model from Edmon02. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.
ONNX export of the SpeechT5 encoder/decoder for faster or edge inference (ONNXRuntime, mobile, C++). Pair with HiFi-GAN vocoder separately.
All-time downloads
63
Public
Repo size
866 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx866 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Oct 20, 2024
- Updated
- Jun 4, 2026
- SHA
- c98fbd62
Base models
Model card
From the Hugging Face model README
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
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- hy
- Created
- Oct 20, 2024
- Updated
- Jun 4, 2026