Automatic Speech Recognition
NeMo
PyTorch
4 languages
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -333,8 +333,8 @@ Another recommended option is to use a json manifest as input, where each line i
333
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
334
  "duration": 10000.0, # duration of the audio
335
  "taskname": "asr", # use "ast" for speech-to-text translation
336
- "source_lang": "en", # Set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
337
- "target_lang": "en", # Language of the text output, choices=['en','de','es','fr']
338
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
339
  }
340
  ```
@@ -365,8 +365,8 @@ An example manifest for transcribing English audios can be:
365
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
366
  "duration": 10000.0, # duration of the audio
367
  "taskname": "asr",
368
- "source_lang": "en",
369
- "target_lang": "en",
370
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
371
  }
372
  ```
@@ -382,8 +382,8 @@ An example manifest for transcribing English audios into German text can be:
382
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
383
  "duration": 10000.0, # duration of the audio
384
  "taskname": "ast",
385
- "source_lang": "en",
386
- "target_lang": "de",
387
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
388
  }
389
  ```
 
333
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
334
  "duration": 10000.0, # duration of the audio
335
  "taskname": "asr", # use "ast" for speech-to-text translation
336
+ "source_lang": "en", # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
337
+ "target_lang": "en", # language of the text output, choices=['en','de','es','fr']
338
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
339
  }
340
  ```
 
365
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
366
  "duration": 10000.0, # duration of the audio
367
  "taskname": "asr",
368
+ "source_lang": "en", # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
369
+ "target_lang": "en", # language of the text output, choices=['en','de','es','fr']
370
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
371
  }
372
  ```
 
382
  "audio_filepath": "/path/to/audio.wav", # path to the audio file
383
  "duration": 10000.0, # duration of the audio
384
  "taskname": "ast",
385
+ "source_lang": "en", # language of the audio input, choices=['en','de','es','fr']
386
+ "target_lang": "de", # language of the text output, choices=['en','de','es','fr']
387
  "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
388
  }
389
  ```