Instructions to use facebook/mms-tts-eng with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/mms-tts-eng with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="facebook/mms-tts-eng")# Load model directly from transformers import AutoTokenizer, AutoModelForTextToWaveform tokenizer = AutoTokenizer.from_pretrained("facebook/mms-tts-eng") model = AutoModelForTextToWaveform.from_pretrained("facebook/mms-tts-eng", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Android + OpenCL implementation β runs on-device on non-flagship phones (Adreno 6xx)
#17
by a8nova - opened
Hi! I wanted to share an Android + OpenCL implementation of MMS-TTS, in case anyone wants to run it on a phone:
- Try it: Edgi on Google Play β runs fully on-device, no cloud.
- Open source: the app is built on top of the open-source adreno-llms inference engine β https://github.com/a8nova/adreno-llms β pure C++/OpenCL with hand-written kernels tuned for Adreno, covering the full VITS pipeline (text encoder + flow + HiFi-GAN).
It's tuned and tested on Adreno 6xx GPUs β the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) β and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it synthesizes at RTF ~1.3 with per-op cosine β₯ 0.996 vs the HF reference β and since all ~1100 MMS language checkpoints share the same architecture, other languages drop straight in.
Hope it's useful β happy to answer questions!