Text-to-Speech
Transformers
Arabic
English
tts
vits
levantine-arabic
code-switching
multi-speaker
streaming
arabic
Instructions to use Tushe/shami-tts-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Tushe/shami-tts-multi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="Tushe/shami-tts-multi")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Tushe/shami-tts-multi", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download benchmark.json from Tushe/shami-tts-multi: direct link, hf CLI and curl.
- Browser
- Download file 278 Bytes
-
https://huggingface.co/Tushe/shami-tts-multi/resolve/main/benchmark.json
- Command line
-
hf download hf://Tushe/shami-tts-multi/benchmark.json
-
curl -L -o benchmark.json https://huggingface.co/Tushe/shami-tts-multi/resolve/main/benchmark.json
278 Bytes
| { | |
| "backend": "torch", | |
| "n_measurements": 15, | |
| "ttfa_ms_p50": 46.3, | |
| "ttfa_ms_p95": 199.0, | |
| "rtf_mean": 0.0329, | |
| "rtf_p95": 0.1114, | |
| "peak_vram_mb": 223.7, | |
| "vram_source": "cuda.max_memory_allocated", | |
| "aggregate_rtf": 0.0318, | |
| "output_sample_rate": 24000 | |
| } |