Updated the model card.

README.md

@@ -3,19 +3,7 @@ language:
 - en
 library_name: nemo
 datasets:
-- librispeech_asr
-- fisher_corpus
-- Switchboard-1
-- WSJ-0
-- WSJ-1
-- National Singapore Corpus Part 1
-- National Singapore Corpus Part 6
-- vctk
-- VoxPopuli (EN)
-- Europarl-ASR (EN)
-- Multilingual LibriSpeech (2000 hours)
-- mozilla-foundation/common_voice_8_0
-- MLCommons/peoples_speech
+- AISHELL-2
 thumbnail: null
 tags:
 - automatic-speech-recognition
@@ -28,123 +16,54 @@ tags:
 - NeMo
 - hf-asr-leaderboard
 license: cc-by-4.0
-widget:
-- example_title: Librispeech sample 1
-  src: https://cdn-media.huggingface.co/speech_samples/sample1.flac
-- example_title: Librispeech sample 2
-  src: https://cdn-media.huggingface.co/speech_samples/sample2.flac
 model-index:
-- name: stt_en_conformer_transducer_xlarge
+- name: stt_zh_conformer_transducer_large
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: LibriSpeech (clean)
-      type: librispeech_asr
-      config: clean
+      name: AISHELL-2 Test IOS
+      type: aishell2_test_ios
+      config: Mandarin
       split: test
       args:
-        language: en
+        language: zh
     metrics:
     - name: Test WER
       type: wer
-      value: 1.62
+      value: 5.3
   - task:
       type: Automatic Speech Recognition
       name: automatic-speech-recognition
     dataset:
-      name: LibriSpeech (other)
-      type: librispeech_asr
-      config: other
+      name: AISHELL-2 Test Android
+      type: aishell2_test_android
+      config: Mandarin
       split: test
       args:
-        language: en
+        language: zh
     metrics:
     - name: Test WER
       type: wer
-      value: 3.01
+      value: 5.7
   - task:
       type: Automatic Speech Recognition
       name: automatic-speech-recognition
     dataset:
-      name: Multilingual LibriSpeech
-      type: facebook/multilingual_librispeech
-      config: english
+      name: AISHELL-2 Test Mic
+      type: aishell2_test_mic
+      config: Mandarin
       split: test
       args:
-        language: en
+        language: zh
     metrics:
     - name: Test WER
       type: wer
-      value: 5.32
-  - task:
-      type: Automatic Speech Recognition
-      name: automatic-speech-recognition
-    dataset:
-      name: Mozilla Common Voice 7.0
-      type: mozilla-foundation/common_voice_7_0
-      config: en
-      split: test
-      args:
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 5.13
-  - task:
-      type: Automatic Speech Recognition
-      name: automatic-speech-recognition
-    dataset:
-      name: Mozilla Common Voice 8.0
-      type: mozilla-foundation/common_voice_8_0
-      config: en
-      split: test
-      args:
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 6.46
-  - task:
-      type: Automatic Speech Recognition
-      name: automatic-speech-recognition
-    dataset:
-      name: Wall Street Journal 92
-      type: wsj_0
-      args:
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 1.17
-  - task:
-      type: Automatic Speech Recognition
-      name: automatic-speech-recognition
-    dataset:
-      name: Wall Street Journal 93
-      type: wsj_1
-      args:
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 2.05
-  - task:
-      type: Automatic Speech Recognition
-      name: automatic-speech-recognition
-    dataset:
-      name: National Singapore Corpus
-      type: nsc_part_1
-      args:
-        language: en
-    metrics:
-    - name: Test WER
-      type: wer
-      value: 5.70
+      value: 5.6
 ---
 
-# NVIDIA Conformer-Transducer X-Large (en-US)
+# NVIDIA Conformer-Transducer Large (zh-ZH)
 
 <style>
 img {
@@ -153,12 +72,12 @@ img {
 </style>
 
 | [![Model architecture](https://img.shields.io/badge/Model_Arch-Conformer--Transducer-lightgrey#model-badge)](#model-architecture)
-| [![Model size](https://img.shields.io/badge/Params-600M-lightgrey#model-badge)](#model-architecture)
-| [![Language](https://img.shields.io/badge/Language-en--US-lightgrey#model-badge)](#datasets)
+| [![Model size](https://img.shields.io/badge/Params-120M-lightgrey#model-badge)](#model-architecture)
+| [![Language](https://img.shields.io/badge/Language-zh--ZH-lightgrey#model-badge)](#datasets)
 
 
-This model transcribes speech in lower case English alphabet along with spaces and apostrophes.
-It is an "extra-large" versions of Conformer-Transducer (around 600M parameters) model.  
+This model transcribes speech in Mandarin alphabet.
+It is a large version of Conformer-Transducer (around 120M parameters) model.  
 See the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#conformer-transducer) for complete architecture details.
 
 ## NVIDIA NeMo: Training
@@ -176,7 +95,7 @@ The model is available for use in the NeMo toolkit [3], and can be used as a pre
 
 ```python
 import nemo.collections.asr as nemo_asr
-asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_en_conformer_transducer_xlarge")
+asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_zh_conformer_transducer_large")
 ```
 
 ### Transcribing using Python
@@ -193,7 +112,7 @@ asr_model.transcribe(['2086-149220-0033.wav'])
 
 ```shell
 python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
- pretrained_name="nvidia/stt_en_conformer_transducer_xlarge" 
+ pretrained_name="nvidia/stt_zh_conformer_transducer_large" 
  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
 ```
 
@@ -213,33 +132,17 @@ Conformer-Transducer model is an autoregressive variant of Conformer model [1] f
 
 The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this [example script](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_transducer/speech_to_text_rnnt_bpe.py) and this [base config](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/conf/conformer/conformer_transducer_bpe.yaml).
 
-The tokenizers for these models were built using the text transcripts of the train set with this [script](https://github.com/NVIDIA/NeMo/blob/main/scripts/tokenizers/process_asr_text_tokenizer.py).
-
 ### Datasets
 
-All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of several thousand hours of English speech:
-
-- Librispeech 960 hours of English speech
-- Fisher Corpus
-- Switchboard-1 Dataset
-- WSJ-0 and WSJ-1
-- National Speech Corpus (Part 1, Part 6)
-- VCTK
-- VoxPopuli (EN)
-- Europarl-ASR (EN)
-- Multilingual Librispeech (MLS EN) - 2,000 hrs subset
-- Mozilla Common Voice (v8.0)
-- People's Speech  - 12,000 hrs subset
-
-Note: older versions of the model may have trained on smaller set of datasets.
+All the models in this collection are trained on AISHELL2 comprising of Mandarin speech:
 
 ## Performance
 
 The list of the available models in this collection is shown in the following table. Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.
 
-| Version | Tokenizer | Vocabulary Size | LS test-other | LS test-clean | WSJ Eval92 | WSJ Dev93 | NSC Part 1 |  MLS Test | MLS Dev | MCV Test 8.0 | Train Dataset |
-|---------|-----------------------|-----------------|---------------|---------------|------------|-----------|-----|-------|------|----|------|
-| 1.10.0 | SentencePiece Unigram | 1024 | 3.01 | 1.62 | 1.17 | 2.05 | 5.70 | 5.32 | 4.59 | 6.46 | NeMo ASRSET 3.0 |
+| Version | Tokenizer | Vocabulary Size | AISHELL2 Test IOS | AISHELL2 Test Android | AISHELL2 Test Mic | Train Dataset |
+|---------|-----------|-----------------|-------------------|-----------------------|-------------------|---------------|
+| 1.10.0  | Characters| 1024            | 5.3               | 5.7                    | 5.6              |     AISHELL-2 |
 
 ## Limitations
 Since this model was trained on publicly available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speech.