Instructions to use alejandro-hp/AlephTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- VoxCPM
How to use alejandro-hp/AlephTTS with VoxCPM:
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("alejandro-hp/AlephTTS") wav = model.generate( text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.", prompt_wav_path=None, # optional: path to a prompt speech for voice cloning prompt_text=None, # optional: reference text cfg_value=2.0, # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse inference_timesteps=10, # LocDiT inference timesteps, higher for better result, lower for fast speed normalize=True, # enable external TN tool denoise=True, # enable external Denoise tool retry_badcase=True, # enable retrying mode for some bad cases (unstoppable) retry_badcase_max_times=3, # maximum retrying times retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech ) sf.write("output.wav", wav, 16000) print("saved: output.wav") - Notebooks
- Google Colab
- Kaggle
Model card: add low-VRAM tip (optimize=False)
Browse files
README.md
CHANGED
|
@@ -63,6 +63,9 @@ Tips:
|
|
| 63 |
- Punctuation shapes delivery: commas and periods add natural pauses, "!" adds energy.
|
| 64 |
- For long text, generate sentence by sentence.
|
| 65 |
- Load the model once and keep it in memory; the first `generate` call after loading includes a warm-up.
|
|
|
|
|
|
|
|
|
|
| 66 |
- `seed=N` (reproducible output) requires a voxcpm release newer than 2.0.3.
|
| 67 |
|
| 68 |
## Model details
|
|
@@ -92,7 +95,8 @@ checkpoint was selected by blind listening tests.
|
|
| 92 |
- Blind listening test by the voice owner (1–5 scale, 10 sentences): **5.0**, tied with real recordings.
|
| 93 |
- Word error rate (Whisper large-v3) on 24 test sentences, including unseen sentences: 0%.
|
| 94 |
- Speaker similarity (ECAPA-TDNN) to held-out real recordings: 0.73–0.76 (real-vs-real: 0.77).
|
| 95 |
-
- On an RTX 3070 Ti: ~5.8 GB VRAM, real-time factor ~0.74,
|
|
|
|
| 96 |
|
| 97 |
## Intended use and limitations
|
| 98 |
|
|
|
|
| 63 |
- Punctuation shapes delivery: commas and periods add natural pauses, "!" adds energy.
|
| 64 |
- For long text, generate sentence by sentence.
|
| 65 |
- Load the model once and keep it in memory; the first `generate` call after loading includes a warm-up.
|
| 66 |
+
- **Low on VRAM?** Load with `VoxCPM.from_pretrained("alejandro-hp/AlephTTS", load_denoiser=False, optimize=False)`.
|
| 67 |
+
This skips `torch.compile`/CUDA graphs: peak VRAM drops to ~5.6 GB at the same speed on an RTX 3070 Ti,
|
| 68 |
+
which helps on 8 GB cards shared with a browser, game or OBS.
|
| 69 |
- `seed=N` (reproducible output) requires a voxcpm release newer than 2.0.3.
|
| 70 |
|
| 71 |
## Model details
|
|
|
|
| 95 |
- Blind listening test by the voice owner (1–5 scale, 10 sentences): **5.0**, tied with real recordings.
|
| 96 |
- Word error rate (Whisper large-v3) on 24 test sentences, including unseen sentences: 0%.
|
| 97 |
- Speaker similarity (ECAPA-TDNN) to held-out real recordings: 0.73–0.76 (real-vs-real: 0.77).
|
| 98 |
+
- On an RTX 3070 Ti: ~5.8 GB VRAM (~5.6 GB with `optimize=False`), real-time factor ~0.74,
|
| 99 |
+
first streaming chunk in under 0.1 s.
|
| 100 |
|
| 101 |
## Intended use and limitations
|
| 102 |
|