Update README.md

README.md

@@ -65,7 +65,7 @@ img {
 | [![Language](https://img.shields.io/badge/Language-en--US-lightgrey#model-badge)](#datasets)
 
 This collection contains large size versions of cache-aware FastConformer-Hybrid (around 114M parameters) with multiple look-ahead support, trained on a large scale english speech. 
-These models are trained for streaming ASR which be used for streaming applications with a variety of latencies. 
+These models are trained for streaming ASR which be used for streaming applications with a variety of latencies (0ms, 80ms, 480s, 1040ms).
 All models are hybrid with both Transducer and CTC decoders. 
 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.
 
@@ -120,8 +120,7 @@ The list of the available models in this collection is shown in the following ta
 ## How to Use this Model
 
 The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for streaming or for fine-tuning on another dataset. 
-
-To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
+You will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
 ```
 pip install nemo_toolkit['all']
 '''
@@ -130,18 +129,36 @@ pip install nemo_toolkit['all']
 pip install nemo_toolkit[all]
 ``` 
 
+### Simulate Streaming ASR
 
 You may use this script to simulate streaming ASR with these models: [cache-aware streaming simulation](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_cache_aware_streaming/speech_to_text_cache_aware_streaming_infer.py). 
-You may use --att_context_size to set the context size otherwise the default which is the first context size in the list is going to be used.
+You may use --att_context_size to set the context size otherwise the default which is the first context size in the list (1040ms) is going to be used.
+
+### Transcribing using Python
+Cache-aware models are designed in a way that the model's predictions are the same in both offline and streaming mode. 
+
+So you may use the regular transcribe function to get the transcriptions. First, let's get a sample:
 
-### Automatically load the model from NGC
+```
+wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
+```
 
-```python
+Then simply do:
+
+```
 import nemo.collections.asr as nemo_asr
 asr_model = nemo_asr.models.EncDecHybridRNNTCTCBPEModel.from_pretrained(model_name="stt_en_fastconformer_hybrid_large_streaming_multi")
+
+#Optional: change the default latency. Default latency is 1040ms. Supported latencies: {0: 0ms, 1: 80ms, 16: 480ms, 33: 1040ms}.
+asr_model.encoder.set_default_att_context_size(33) 
+
+#Optional: change the default decoder. Default decoder is Transducer (RNNT). Supported decoders: {ctc, rnnt}.
+asr_model.change_decoding_strategy(decoder_type='rnnt')
+
+asr_model.transcribe(['2086-149220-0033.wav'])
 ```
 
-### Transcribing text with this model
+### Transcribing many audio files
 
 Using Transducer mode inference:
 
@@ -168,6 +185,7 @@ python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py \
   audio_dir="<DIRECTORY CONTAINING AUDIO FILES>" \
   att_context_size=[70,0]
 ```
+Supported values for att_context_size: {[70,0]: 0ms, [70,1]: 80ms, [70,16]: 480ms, [70,33]: 1040ms}.
 
 ### Input
 
@@ -177,108 +195,6 @@ This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
 
 This model provides transcribed speech as a string for a given audio sample.
 
-## Limitations
-
-Since this model was trained on publically 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.
-
-
-## References
-
-
-[1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
-
-[2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
-
-[3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
-
-[4] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)
-
-
-
-## NVIDIA NeMo: Training
-
-To train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest Pytorch version.
-```
-pip install nemo_toolkit['all']
-'''
-'''
-(if it causes an error): 
-pip install nemo_toolkit[all]
-``` 
-
-## How to Use this Model
-
-The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.
-
-### Automatically instantiate the model
-
-```python
-import nemo.collections.asr as nemo_asr
-asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_en_conformer_transducer_xlarge")
-```
-
-### Transcribing using Python
-First, let's get a sample
-```
-wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
-```
-Then simply do:
-```
-asr_model.transcribe(['2086-149220-0033.wav'])
-```
-
-### Transcribing many audio files
-
-```shell
-python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
- pretrained_name="nvidia/stt_en_conformer_transducer_xlarge" 
- audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
-```
-
-### Input
-
-This model accepts 16000 KHz Mono-channel Audio (wav files) as input.
-
-### Output
-
-This model provides transcribed speech as a string for a given audio sample.
-
-## Model Architecture
-
-Conformer-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding instead of CTC Loss. You may find more info on the detail of this model here: [Conformer-Transducer Model](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html). 
-
-## Training
-
-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.
-
-## 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 |
-
 ## 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.
 
@@ -295,10 +211,12 @@ Although this model isn’t supported yet by Riva, the [list of supported models
 Check out [Riva live demo](https://developer.nvidia.com/riva#demos). 
 
 ## References
+
+
 [1] [Conformer: Convolution-augmented Transformer for Speech Recognition](https://arxiv.org/abs/2005.08100)
+
 [2] [Google Sentencepiece Tokenizer](https://github.com/google/sentencepiece)
-[3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
 
-## Licence
+[3] [NVIDIA NeMo Toolkit](https://github.com/NVIDIA/NeMo)
 
-License to use this model is covered by the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/). By downloading the public and release version of the model, you accept the terms and conditions of the [CC-BY-4.0](https://creativecommons.org/licenses/by/4.0/) license.
+[4] [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://arxiv.org/abs/2305.05084)