Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
Safetensors
whisper
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use openai/whisper-tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-tiny with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-tiny") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-tiny", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Android + OpenCL implementation — runs on-device on non-flagship phones (Adreno 6xx)
#48
by a8nova - opened
Hi! I wanted to share an Android + OpenCL implementation of Whisper-tiny, in case anyone wants to run it on a phone:
- Try it: Edgi on Google Play — runs fully on-device, no cloud.
- Open source: the app is built on top of the open-source adreno-llms inference engine — https://github.com/a8nova/adreno-llms — pure C++/OpenCL with hand-written kernels tuned for Adreno.
It's tuned and tested on Adreno 6xx GPUs — the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) — and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it transcribes faster than real time (RTF ~0.53 on LibriSpeech clips) and has a live streaming transcription mode.
Hope it's useful — happy to answer questions!