nvidia
/

canary-1b

Automatic Speech Recognition

automatic-speech-translation

hf-asr-leaderboard

Model card Files Files and versions Community

steveheh commited on Feb 8

Commit

b8d8535

•

1 Parent(s): ecb83a9

Update README.md

Files changed (1) hide show

README.md +6 -6

README.md CHANGED Viewed

@@ -333,8 +333,8 @@ Another recommended option is to use a json manifest as input, where each line i
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "asr",  # use "ast" for speech-to-text translation
-    "source_lang": "en",  # Set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
-    "target_lang": "en",  # Language of the text output, choices=['en','de','es','fr']
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```
@@ -365,8 +365,8 @@ An example manifest for transcribing English audios can be:
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "asr",
-    "source_lang": "en",
-    "target_lang": "en",
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```
@@ -382,8 +382,8 @@ An example manifest for transcribing English audios into German text can be:
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "ast",
-    "source_lang": "en",
-    "target_lang": "de",
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```

     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "asr",  # use "ast" for speech-to-text translation
+    "source_lang": "en",  # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
+    "target_lang": "en",  # language of the text output, choices=['en','de','es','fr']
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "asr",
+    "source_lang": "en", # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
+    "target_lang": "en", # language of the text output, choices=['en','de','es','fr']
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
     "duration": 10000.0,  # duration of the audio
     "taskname": "ast",
+    "source_lang": "en", # language of the audio input, choices=['en','de','es','fr']
+    "target_lang": "de", # language of the text output, choices=['en','de','es','fr']
     "pnc": "yes",  # whether to have PnC output, choices=['yes', 'no']
 }
 ```