Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
Transducer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results
nithinraok commited on
Commit
5683bc0
1 Parent(s): 3b91bdf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -3
README.md CHANGED
@@ -163,7 +163,7 @@ metrics:
163
  pipeline_tag: automatic-speech-recognition
164
  ---
165
 
166
- # Parakeet Hybrid PnC 1.1B (en)
167
 
168
  <style>
169
  img {
@@ -195,7 +195,7 @@ The model is available for use in the NeMo toolkit [3], and can be used as a pre
195
 
196
  ```python
197
  import nemo.collections.asr as nemo_asr
198
- asr_model = nemo_asr.models.ASRModel.from_pretrained(model_name="nvidia/parakeet-hyb-pnc-1.1b")
199
  ```
200
 
201
  ### Transcribing using Python
@@ -214,7 +214,7 @@ By default model uses TDT to transcribe the audio files, to switch decoder to us
214
 
215
  ```shell
216
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
217
- pretrained_name="nvidia/parakeet-hyb-pnc-1.1b"
218
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
219
  ```
220
 
 
163
  pipeline_tag: automatic-speech-recognition
164
  ---
165
 
166
+ # Parakeet TDT-CTC 1.1B PnC(en)
167
 
168
  <style>
169
  img {
 
195
 
196
  ```python
197
  import nemo.collections.asr as nemo_asr
198
+ asr_model = nemo_asr.models.ASRModel.from_pretrained(model_name="nvidia/parakeet-tdt_ctc-1.1b")
199
  ```
200
 
201
  ### Transcribing using Python
 
214
 
215
  ```shell
216
  python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py
217
+ pretrained_name="nvidia/parakeet-tdt_ctc-1.1b"
218
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
219
  ```
220