Xenova HF staff commited on
Commit
6010b1b
1 Parent(s): 7ff7624

Add listed support for Transformers.js (#5)

Browse files

- Add listed support for Transformers.js (80a5bd0913d452972110d431b0c4b4ce27e57f62)

Files changed (1) hide show
  1. README.md +16 -0
README.md CHANGED
@@ -4,6 +4,7 @@ language:
4
  tags:
5
  - audio
6
  - automatic-speech-recognition
 
7
  widget:
8
  - example_title: LibriSpeech sample 1
9
  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
@@ -244,6 +245,21 @@ Coming soon ...
244
 
245
  Coming soon ...
246
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
247
  ## Model Details
248
 
249
  Distil-Whisper inherits the encoder-decoder architecture from Whisper. The encoder maps a sequence of speech vector
 
4
  tags:
5
  - audio
6
  - automatic-speech-recognition
7
+ - transformers.js
8
  widget:
9
  - example_title: LibriSpeech sample 1
10
  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
 
245
 
246
  Coming soon ...
247
 
248
+ ### Transformers.js
249
+
250
+ ```js
251
+ import { pipeline } from '@xenova/transformers';
252
+
253
+ let transcriber = await pipeline('automatic-speech-recognition', 'distil-whisper/distil-medium.en');
254
+
255
+ let url = 'https://huggingface.co/datasets/Xenova/transformers.js-docs/resolve/main/jfk.wav';
256
+ let output = await transcriber(url);
257
+ // { text: " And so my fellow Americans, ask not what your country can do for you. Ask what you can do for your country." }
258
+ ```
259
+
260
+ See the [docs](https://huggingface.co/docs/transformers.js/api/pipelines#module_pipelines.AutomaticSpeechRecognitionPipeline) for more information.
261
+
262
+
263
  ## Model Details
264
 
265
  Distil-Whisper inherits the encoder-decoder architecture from Whisper. The encoder maps a sequence of speech vector