Create README.md

README.md

@@ -0,0 +1,64 @@
+---
+language: vi
+datasets:
+- vlsp-asr-2020
+tags:
+- audio
+- automatic-speech-recognition
+license: cc-by-nc-4.0
+---
+
+## Model description
+
+Our models use wav2vec2 architecture, pre-trained on 13k hours of Vietnamese youtube audio (un-label data) and fine-tuned on 250 hours labeled of VLSP ASR dataset on 16kHz sampled speech audio. You can find more description [here](https://github.com/nguyenvulebinh/vietnamese-wav2vec2)
+
+## Benchmark WER result on VLSP T1 testset:
+
+| | [base model](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi-vlsp2020) | [large model](https://huggingface.co/nguyenvulebinh/wav2vec2-base-vi-vlsp2020) |
+|---|---|---|
+|without LM| 8.66  | 6.90 |
+|with 5-grams LM| 6.53 | 5.32 |
+
+## Usage
+
+```python
+#pytorch
+#!pip install transformers==4.20.0
+#!pip install https://github.com/kpu/kenlm/archive/master.zip
+#!pip install pyctcdecode==0.4.0
+from transformers.file_utils import cached_path, hf_bucket_url
+from importlib.machinery import SourceFileLoader
+from transformers import Wav2Vec2ProcessorWithLM
+from IPython.lib.display import Audio
+import torchaudio
+import torch
+
+# Load model & processor
+model_name = "nguyenvulebinh/wav2vec2-large-vi-vlsp2020"
+model = SourceFileLoader("model", cached_path(hf_bucket_url(model_name,filename="model_handling.py"))).load_module().Wav2Vec2ForCTC.from_pretrained(model_name)
+processor = Wav2Vec2ProcessorWithLM.from_pretrained(model_name)
+
+# Load an example audio (16k)
+audio, sample_rate = torchaudio.load(cached_path(hf_bucket_url(model_name, filename="t2_0000006682.wav")))
+input_data = processor.feature_extractor(audio[0], sampling_rate=16000, return_tensors='pt')
+
+# Infer
+output = model(**input_data)
+
+# Output transcript without LM
+print(processor.tokenizer.decode(output.logits.argmax(dim=-1)[0].detach().cpu().numpy()))
+
+# Output transcript with LM
+print(processor.decode(output.logits.cpu().detach().numpy()[0], beam_width=100).text)
+```
+
+### Model Parameters License
+
+The ASR model parameters are made available for non-commercial use only, under the terms of the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) license. You can find details at: https://creativecommons.org/licenses/by-nc/4.0/legalcode
+
+
+### Contact 
+
+[email protected]
+
+[![Follow](https://img.shields.io/twitter/follow/nguyenvulebinh?style=social)](https://twitter.com/intent/follow?screen_name=nguyenvulebinh)