Automatic Speech Recognition
NeMo
PyTorch
4 languages
automatic-speech-translation
speech
audio
Transformer
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results

adding answer field to manifest line

#13
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -335,7 +335,8 @@ Another recommended option is to use a json manifest as input, where each line i
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
  ```
341
 
@@ -367,7 +368,8 @@ An example manifest for transcribing English audios can be:
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
  ```
373
 
@@ -384,7 +386,8 @@ An example manifest for transcribing English audios into German text can be:
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
  ```
390
 
 
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
+ "answer": "na",
340
  }
341
  ```
342
 
 
368
  "taskname": "asr",
369
  "source_lang": "en", # language of the audio input, set `source_lang`==`target_lang` for ASR, choices=['en','de','es','fr']
370
  "target_lang": "en", # language of the text output, choices=['en','de','es','fr']
371
+ "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
372
+ "answer": "na",
373
  }
374
  ```
375
 
 
386
  "taskname": "ast",
387
  "source_lang": "en", # language of the audio input, choices=['en','de','es','fr']
388
  "target_lang": "de", # language of the text output, choices=['en','de','es','fr']
389
+ "pnc": "yes", # whether to have PnC output, choices=['yes', 'no']
390
+ "answer": "na"
391
  }
392
  ```
393