aismlv / zindi-ai4d-wolof
4th place solution to Zindi's low-resource automatic speech recognition competition
☆8Updated 3 years ago
Alternatives and similar repositories for zindi-ai4d-wolof:
Users that are interested in zindi-ai4d-wolof are comparing it to the libraries listed below
- Audio Preprocessing and finetuning of wav2vec2-large-xlsr model on AI4D Baamtu Datamation - Automatic Speech Recognition in WOLOF Data.☆17Updated 3 years ago
- A merged version of multiple open-source German speech datasets.☆31Updated 11 months ago
- Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode☆111Updated 2 years ago
- Repository containing experimentation platform on how to train, infer on wav2vec2 models.☆86Updated 2 years ago
- ☆43Updated 2 years ago
- Transcribing audio files using Hugging Face's implementation of Wav2Vec2 + "chain-linking" NLP tasks to combine speech-to-text with downs…☆31Updated 4 years ago
- ☆42Updated 3 years ago
- ☆46Updated 2 years ago
- Various speech datasets made available to the public☆116Updated 4 months ago
- GSoC'2021 | TensorFlow implementation of Wav2Vec2☆91Updated 3 years ago
- Incorporating KenLM language model with HuggingFace implementation of Wav2Vec2CTC Model using beam search decoding☆75Updated 3 years ago
- Punctuation Restoration using Transformer Models for High-and Low-Resource Languages☆212Updated 8 months ago
- Example code for a neural transducer model.☆61Updated last year
- Speech to Text with self-supervised learning based on wav2vec 2.0 framework using Hugging Face's Transformer☆30Updated 3 years ago
- PyTorch implementation of "Squeezeformer: An Efficient Transformer for Automatic Speech Recognition" (NeurIPS 2022)☆140Updated 2 years ago
- A PyPI package for fast word/character error rate (WER/CER) calculation☆71Updated last year
- This is an ASR corpus for Bemba language. It contains read speech from diverse publicly available Bemba sources; Literature Books, Radio/…☆35Updated 4 months ago
- An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.☆82Updated last year
- [NeurIPS'22] Squeezeformer: An Efficient Transformer for Automatic Speech Recognition☆251Updated 2 years ago
- Finetune Wa2vec 2.0 For Speech Recognition☆129Updated 2 months ago
- Multilingual and code-switching ASR challenges for low resource Indian languages.☆20Updated 3 years ago
- This will hold the data pipeline to convert raw audio data to speech which will act as input dataset for speech-to-text pipeline☆32Updated 2 years ago
- Vaksanca introduces free Sanskrit speech corpus with vowel segmentation.☆15Updated 3 years ago
- Repository containing the open source code of works published at the FBK MT unit.☆43Updated last week
- An implementation for "Conformer: Convolution-augmented Transformer for Speech Recognition" Paper☆18Updated 2 years ago
- ☆187Updated 3 years ago
- ASRecognition: just an easy-to-use library for Automatic Speech Recognition.☆51Updated 2 years ago
- [Computer Speech & Language] A transformer-based spelling error correction framework for Bangla and resource scarce Indic languages☆12Updated 8 months ago
- Rescoring methods for end-to-end Automatic Speech Recognition☆27Updated 4 years ago
- Pretraining, fine-tuning and evaluation scripts for Indic-Wav2Vec2☆85Updated last year