Automatic Speech Recognition
Transformers
Safetensors
Japanese
whisper
audio
hf-asr-leaderboard
asahi417 commited on
Commit
58e589d
·
verified ·
1 Parent(s): 4bdaa6e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -113,7 +113,7 @@ pipe = pipeline(
113
  chunk_length_s=15,
114
  batch_size=16,
115
  trust_remote_code=True,
116
- stable_ts=True,
117
  punctuator=True
118
  )
119
 
@@ -132,13 +132,13 @@ print(result)
132
  + result = pipe("audio.mp3", return_timestamps=True, generate_kwargs=generate_kwargs)
133
  ```
134
 
135
- - To deactivate stable-ts:
136
  ```diff
137
- - stable_ts=True,
138
- + stable_ts=False,
139
  ```
140
 
141
- - To deactivate punctuator:
142
  ```diff
143
  - punctuator=True,
144
  + punctuator=False,
 
113
  chunk_length_s=15,
114
  batch_size=16,
115
  trust_remote_code=True,
116
+ stable_ts=False,
117
  punctuator=True
118
  )
119
 
 
132
  + result = pipe("audio.mp3", return_timestamps=True, generate_kwargs=generate_kwargs)
133
  ```
134
 
135
+ - As default, stable-ts is deactivated. To activate stable-ts:
136
  ```diff
137
+ - stable_ts=False,
138
+ + stable_ts=True,
139
  ```
140
 
141
+ - As default, punctuator is activated. To deactivate punctuator:
142
  ```diff
143
  - punctuator=True,
144
  + punctuator=False,