加载中…
加载中…
openai/whisper-baseonnx/decoder_model_merged.onnx 209 MBonnx/decoder_model.onnx 208 MBonnx/decoder_with_past_model.onnx 196 MBonnx/decoder_model_uint8.onnx 159 MBonnx/decoder_model_int8.onnx 159 MBonnx/decoder_with_past_model_uint8.onnx 156 MBonnx/decoder_with_past_model_int8.onnx 156 MBonnx/decoder_model_merged_q4.onnx 124 MBonnx/decoder_model_q4.onnx 123 MBonnx/decoder_model_merged_bnb4.onnx 122 MBonnx/decoder_model_bnb4.onnx 122 MBonnx/decoder_with_past_model_q4.onnx 121 MBonnx/decoder_with_past_model_bnb4.onnx 120 MBonnx/decoder_model_merged_fp16.onnx 105 MBonnx/decoder_model_fp16.onnx 104 MBonnx/decoder_with_past_model_fp16.onnx 98 MBonnx/encoder_model.onnx 82 MBonnx/decoder_model_merged_q4f16.onnx 69 MBonnx/decoder_model_q4f16.onnx 68 MBonnx/decoder_with_past_model_q4f16.onnx 66 MBonnx/decoder_model_merged_uint8.onnx 54 MBonnx/decoder_model_merged_int8.onnx 54 MBonnx/decoder_model_merged_quantized.onnx 54 MBonnx/decoder_model_quantized.onnx 53 MBonnx/decoder_with_past_model_quantized.onnx 50 MBonnx/encoder_model_fp16.onnx 41 MBonnx/encoder_model_quantized.onnx 23 MBonnx/encoder_model_uint8.onnx 23 MBonnx/encoder_model_q4.onnx 19 MBonnx/encoder_model_bnb4.onnx 18 MBonnx/encoder_model_q4f16.onnx 14 MBhttps://huggingface.co/openai/whisper-base with ONNX weights to be compatible with Transformers.js.
If you haven't already, you can install the Transformers.js JavaScript library from NPM using:
npm i @huggingface/transformers
Example: Transcribe audio from a URL.
import { pipeline } from '@huggingface/transformers';
const transcriber = await pipeline('automatic-speech-recognition', 'Xenova/whisper-base');
const url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
const output = await transcriber(url);
Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using 🤗 Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).