Data

Tools

Indexes

Applications

Experiments

Open Source Science

slu-asr

https://github.com/haipham03/slu-asr

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.2%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: haipham03
  • Language: Python
  • Default Branch: main
  • Size: 5.61 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme Citation

README.md

Training

  1. Prepare your dataset
    • To put your dataset in correct format and process it run: bash prepare_train_data.sh [Path to wav data directory] [Path to jsonline train file]
    • Example : cmd bash prepare_train_data.sh SLU_data/train_data/Train/ SLU_data/train.jsonl
    • The processed data will be store in txt_data/process_train.txt
  2. Run
    • Start training from scratch: cmd python train.py -c config.toml
    • Change the number of workers, epochs, batch size, vv in config.toml

Inference

bash inference.sh [Path to your wav test file lists] [Path to model.tar] [Path to LM model]

  • Example: bash inference.sh data/public_test/ saved/ASR/checkpoints/best_model.tar your_3gram.binary

  • Then the final transcript be in process_trans_file.txt

Owner

  • Name: Phạm Hoàng Hải
  • Login: haipham03
  • Kind: user

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!
cff-version: 1.2.0
title: >-
  Finetune Wav2vec 2.0 For Speech
  Recognition
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: Le
    family-names: Khanh
    name-particle: Duy
    email: khanhld218@uef.edu.vn
identifiers:
  - type: doi
    value: 10.5281/zenodo.6540979
repository-code: 'https://github.com/khanld/ASR-Wa2vec-Finetune'
url: >-
  https://github.com/khanld/ASR-Wa2vec-Finetune
keywords:
  - asr
date-released: 2022-05-12
doi: 10.5281/zenodo.6540979

GitHub Events

Total
  • Delete event: 1
  • Push event: 2
Last Year
  • Delete event: 1
  • Push event: 2

Issues and Pull Requests

Last synced: 12 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • datasets ==2.1.0
  • huggingface_hub ==0.5.1
  • librosa ==0.9.1
  • numpy ==1.22.0
  • pandarallel ==1.6.1
  • pandas ==1.4.2
  • scikit_learn ==1.0.2
  • tensorflow ==2.8.1
  • toml ==0.10.2
  • torch ==1.7.1
  • tqdm ==4.64.0
  • transformers ==4.18.0