smajumdar94 nkarpov commited on
Commit
a858311
1 Parent(s): 4ae36d5

Update README.md (#1)

Browse files

- Update README.md (ec71b60876ba7ab49b386e1d90462d52152a6e08)


Co-authored-by: Nikolay <nkarpov@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +5 -5
README.md CHANGED
@@ -44,14 +44,14 @@ model-index:
44
  config: Ukrainian P&C
45
  split: test
46
  args:
47
- language: uk
48
  metrics:
49
  - name: Test WER P&C
50
  type: wer
51
  value: 6.92
52
  ---
53
 
54
- # NVIDIA FastConformer-Hybrid Large (uk)
55
 
56
  <style>
57
  img {
@@ -83,7 +83,7 @@ The model is available for use in the NeMo toolkit [3], and can be used as a pre
83
 
84
  ```python
85
  import nemo.collections.asr as nemo_asr
86
- asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name="nvidia/stt_uk_fastconformer_hybrid_large_pc")
87
  ```
88
 
89
  ### Transcribing using Python
@@ -101,14 +101,14 @@ asr_model.transcribe(['2086-149220-0033.wav'])
101
  Using Transducer mode inference:
102
  ```shell
103
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
104
- pretrained_name="nvidia/stt_uk_fastconformer_hybrid_large_pc"
105
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
106
  ```
107
 
108
  Using CTC mode inference:
109
  ```shell
110
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
111
- pretrained_name="nvidia/stt_uk_fastconformer_hybrid_large_pc"
112
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
113
  decoder_type="ctc"
114
  ```
 
44
  config: Ukrainian P&C
45
  split: test
46
  args:
47
+ language: ua
48
  metrics:
49
  - name: Test WER P&C
50
  type: wer
51
  value: 6.92
52
  ---
53
 
54
+ # NVIDIA FastConformer-Hybrid Large (ua)
55
 
56
  <style>
57
  img {
 
83
 
84
  ```python
85
  import nemo.collections.asr as nemo_asr
86
+ asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name="nvidia/stt_ua_fastconformer_hybrid_large_pc")
87
  ```
88
 
89
  ### Transcribing using Python
 
101
  Using Transducer mode inference:
102
  ```shell
103
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
104
+ pretrained_name="nvidia/stt_ua_fastconformer_hybrid_large_pc"
105
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
106
  ```
107
 
108
  Using CTC mode inference:
109
  ```shell
110
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
111
+ pretrained_name="nvidia/stt_ua_fastconformer_hybrid_large_pc"
112
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
113
  decoder_type="ctc"
114
  ```