Update readme, `whisper-large` -> `whisper-large-v2`

#4
by ArthurZ HF staff - opened
Files changed (1) hide show
  1. README.md +9 -9
README.md CHANGED
@@ -174,8 +174,8 @@ The "<|en|>" token is used to specify that the speech is in english and should b
174
  >>> import torch
175
 
176
  >>> # load model and processor
177
- >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
178
- >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
179
 
180
  >>> # load dummy dataset and read soundfiles
181
  >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
@@ -199,8 +199,8 @@ transcription.
199
  >>> import torch
200
 
201
  >>> # load model and processor
202
- >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
203
- >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
204
 
205
  >>> # load dummy dataset and read soundfiles
206
  >>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
@@ -227,8 +227,8 @@ The "<|translate|>" is used as the first decoder input token to specify the tran
227
  >>> import torch
228
 
229
  >>> # load model and processor
230
- >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
231
- >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large")
232
 
233
  >>> # load dummy dataset and read soundfiles
234
  >>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
@@ -245,7 +245,7 @@ The "<|translate|>" is used as the first decoder input token to specify the tran
245
 
246
  ## Evaluation
247
 
248
- This code snippet shows how to evaluate **openai/whisper-large** on LibriSpeech's "clean" and "other" test data.
249
 
250
  ```python
251
  >>> from datasets import load_dataset
@@ -257,8 +257,8 @@ This code snippet shows how to evaluate **openai/whisper-large** on LibriSpeech'
257
 
258
  >>> librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
259
 
260
- >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large").to("cuda")
261
- >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large")
262
 
263
  >>> def map_to_pred(batch):
264
  >>> input_features = processor(batch["audio"]["array"], return_tensors="pt").input_features
 
174
  >>> import torch
175
 
176
  >>> # load model and processor
177
+ >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large-v2")
178
+ >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2")
179
 
180
  >>> # load dummy dataset and read soundfiles
181
  >>> ds = load_dataset("hf-internal-testing/librispeech_asr_dummy", "clean", split="validation")
 
199
  >>> import torch
200
 
201
  >>> # load model and processor
202
+ >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large-v2")
203
+ >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2")
204
 
205
  >>> # load dummy dataset and read soundfiles
206
  >>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
 
227
  >>> import torch
228
 
229
  >>> # load model and processor
230
+ >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large-v2")
231
+ >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2")
232
 
233
  >>> # load dummy dataset and read soundfiles
234
  >>> ds = load_dataset("common_voice", "fr", split="test", streaming=True)
 
245
 
246
  ## Evaluation
247
 
248
+ This code snippet shows how to evaluate **openai/whisper-large-v2** on LibriSpeech's "clean" and "other" test data.
249
 
250
  ```python
251
  >>> from datasets import load_dataset
 
257
 
258
  >>> librispeech_eval = load_dataset("librispeech_asr", "clean", split="test")
259
 
260
+ >>> model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-large-v2").to("cuda")
261
+ >>> processor = WhisperProcessor.from_pretrained("openai/whisper-large-v2")
262
 
263
  >>> def map_to_pred(batch):
264
  >>> input_features = processor(batch["audio"]["array"], return_tensors="pt").input_features