README.md

---
language:
- en
tags:
- esb
datasets:
- esb/datasets
- revdotcom/earnings22
---

To reproduce this run, first call `get_ctc_tokenizer.py` to train the CTC tokenizer and then execute the following command to train the CTC system: 
```python 
#!/usr/bin/env bash
python run_flax_speech_recognition_ctc.py \
        --model_name_or_path="esb/wav2vec2-ctc-pretrained" \
        --tokenizer_name="wav2vec2-ctc-earnings22-tokenizer" \
        --dataset_name="esb/datasets" \
        --dataset_config_name="earnings22" \
        --output_dir="./" \
        --wandb_project="wav2vec2-ctc" \
        --wandb_name="wav2vec2-ctc-earnings22" \
        --max_steps="50000" \
        --save_steps="10000" \
        --eval_steps="10000" \
        --learning_rate="3e-4" \
        --logging_steps="25" \
        --warmup_steps="5000" \
        --preprocessing_num_workers="1" \
        --hidden_dropout="0.2" \
        --activation_dropout="0.2" \
        --feat_proj_dropout="0.2" \
        --do_train \
        --do_eval \
        --do_predict \
        --overwrite_output_dir \
        --gradient_checkpointing \
        --freeze_feature_encoder \
        --push_to_hub \
        --use_auth_token
```