Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/vaibhavs10/how-to-asr
https://github.com/vaibhavs10/how-to-asr
Last synced: 12 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/vaibhavs10/how-to-asr
- Owner: Vaibhavs10
- Created: 2022-07-04T18:24:05.000Z (over 2 years ago)
- Default Branch: main
- Last Pushed: 2022-08-29T13:20:08.000Z (about 2 years ago)
- Last Synced: 2023-08-26T05:22:31.395Z (about 1 year ago)
- Language: Jupyter Notebook
- Size: 2.13 MB
- Stars: 14
- Watchers: 3
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# How to ASR!?
Delivered by: [Vaibhav Srivastav](https://twitter.com/reach_vb)
Collection of notebooks to build Speech Recognition models the easy way! <3
## Contents of the workshop
1. ASR from ground up!
2. Fine-tune your ASR model (Wav2Vec2)
3. Package your ASR model into a web-app
## Intersted in building more such cool Gradio apps and demos?
We're running a Gradio hackathon in collaboration with Hugging Face: https://huggingface.co/EuroSciPy2022
Catch me around during the conference if you need help or want some support :)
## Further reading
1. XLSR-Wav2Vec2 paper - https://arxiv.org/abs/2006.13979
2. Build CTC & Seq2Seq ASR models - [Transformers examples repo](https://github.com/huggingface/transformers/tree/main/examples/pytorch/speech-recognition#connectionist-temporal-classification-without-language-model-ctc-wo-lm)
3. Boost your ASR model's performance with a Language Model - https://huggingface.co/blog/wav2vec2-with-ngram
4. Infer your ASR model on large files/ live - https://huggingface.co/blog/asr-chunking
## Got any questions?
Hit me up on [twitter](https://twitter.com/reach_vb)/ [[email protected]](mailto:[email protected])