nvidia
/

canary-1b

Automatic Speech Recognition

automatic-speech-translation

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

steveheh commited on Feb 16, 2024

Commit

c83fad4

·

verified ·

1 Parent(s): fd9c3e7

Update README.md

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -331,7 +331,7 @@ Another recommended option is to use a json manifest as input, where each line i
 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
-    "duration": None,  # 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']
@@ -364,7 +364,7 @@ An example manifest for transcribing English audios can be:
 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
-    "duration": None,  # 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']
@@ -382,7 +382,7 @@ An example manifest for transcribing English audios into German text can be:
 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
-    "duration": None,  # 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']

 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
+    "duration": [SET TO THE ACTUAL DURATION OF AUDIO],  # 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']
 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
+    "duration": [SET TO THE ACTUAL DURATION OF AUDIO],  # 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']
 # Example of a line in input_manifest.json
 {
     "audio_filepath": "/path/to/audio.wav",  # path to the audio file
+    "duration": [SET TO THE ACTUAL DURATION OF AUDIO],  # 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']