ai4bharat
/

indicconformer_stt_te_hybrid_ctc_rnnt_large

Automatic Speech Recognition

Model card Files Files and versions Community

kaushal98b commited on Sep 18

Commit

137d9a7

•

1 Parent(s): d0a145d

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -48,13 +48,13 @@ library_name: nemo
   ### Inference using CTC decoder
   ```
   model.cur_decoder = "ctc"
-  ctc_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1,logprobs=False, language_id='hi')[0]
   print(ctc_text)
   ```
   ### Inference using RNNT decoder
   ```
   model.cur_decoder = "rnnt"
-  rnnt_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1, language_id='hi')[0]
   print(rnnt_text)
   ```

   ### Inference using CTC decoder
   ```
   model.cur_decoder = "ctc"
+  ctc_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1,logprobs=False, language_id='te')[0]
   print(ctc_text)
   ```
   ### Inference using RNNT decoder
   ```
   model.cur_decoder = "rnnt"
+  rnnt_text = model.transcribe(['sample_audio_infer_ready.wav'], batch_size=1, language_id='te')[0]
   print(rnnt_text)
   ```