Hugging Face's logo

nvidia
/
stt_pt_fastconformer_hybrid_large_pc

Automatic Speech Recognition
NeMo
Portuguese
FastConformer
NeMo
Portuguese
Model card Files
xet
Community
2
Nune1 commited on
Commit
30cc336
·
verified ·
1 Parent(s): 46d0ffa

Update

Browse files
Files changed (1) hide show
  1. README.md +2 -2
README.md CHANGED
@@ -55,14 +55,14 @@ asr_model.transcribe([path_to_audio_file])
55
  Using Transducer mode inference:
56
  ```shell
57
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
58
- pretrained_name="nvidia/stt_fa_fastconformer_hybrid_large"
59
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
60
  ```
61
 
62
  Using CTC mode inference:
63
  ```shell
64
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
65
- pretrained_name="nvidia/stt_fa_fastconformer_hybrid_large"
66
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
67
  decoder_type="ctc"
68
  ```
 
55
  Using Transducer mode inference:
56
  ```shell
57
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
58
+ pretrained_name="nvidia/stt_pt_fastconformer_hybrid_large"
59
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
60
  ```
61
 
62
  Using CTC mode inference:
63
  ```shell
64
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
65
+ pretrained_name="nvidia/stt_pt_fastconformer_hybrid_large"
66
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
67
  decoder_type="ctc"
68
  ```