Update README.md

README.md

@@ -1,9 +1,6 @@
 ---
-
-
-
 language:
-- be
+- en
 library_name: nemo
 datasets:
 - mozilla-foundation/common_voice_10_0
@@ -36,9 +33,10 @@ model-index:
     - name: Test WER
       type: wer
       value: 3.8
-  
+
 ---
-# NVIDIA Conformer-RNNT Large (be)
+
+# NVIDIA Conformer-Transducer Large (be-Bel)
 
 <style>
 img {
@@ -51,21 +49,50 @@ img {
 | [![Language](https://img.shields.io/badge/Language-be--Belarusian-lightgrey#model-badge)](#datasets)
 
 
-This model transcribes speech in lowercase Belarusian alphabet including spaces and apostrophes, and is trained on few hundreds of Belarusian speech data.
-It is a "large" variant of Conformer, with around 120 million parameters.
+This model transcribes speech in lower case Belarusian alphabet along with spaces and apostrophes.
+It is an "large" versions 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
+
+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]
+``` 
 
-## Usage
+## 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.
 
-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.
+### Automatically instantiate the model
 
+```python
+import nemo.collections.asr as nemo_asr
+asr_model = nemo_asr.models.EncDecRNNTBPEModel.from_pretrained("nvidia/stt_be_conformer_transducer_large")
 ```
-pip install nemo_toolkit['all']
+
+### Transcribing many audio files
+
+```shell
+python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py 
+ pretrained_name="nvidia/stt_be_conformer_transducer_large" 
+ audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"
 ```
 
+### Input
+
+This model accepts 16000 Hz 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
@@ -75,12 +102,23 @@ The NeMo toolkit [3] was used for training the models for over several hundred e
 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 hundreds hours of Belarusian speech:
+
 - Mozilla Common Voice (v10.0)
+
+
 ## Performance
-Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding. WER on dev is 3.8%
+
+Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding. 
+
+| Version | Tokenizer            | Vocabulary Size | MCV 10 Test | Train Dataset |
+|---------|----------------------|-----------------|-------------|---------------|
+| 1.12.0  | Google Sentencepiece | 1024            | 3.8         | MCV 10        |
+
 ## Limitations
-Since all models are trained on just MCV-10 dataset, 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.
+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.
+
 ## NVIDIA Riva: Deployment
 
 [NVIDIA Riva](https://developer.nvidia.com/riva), is an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, on edge, and embedded.