File size: 1,286 Bytes
f1223e8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
---
language:
- en
tags:
- esb
datasets:
- esb/datasets
- LIUM/tedlium
---
To reproduce this run, execute:
```python
#!/usr/bin/env bash
python run_flax_speech_recognition_seq2seq.py \
--dataset_name="esb/datasets" \
--model_name_or_path="esb/wav2vec2-aed-tedlium" \
--dataset_config_name="tedlium" \
--output_dir="./" \
--wandb_name="wav2vec2-aed-tedlium" \
--wandb_project="wav2vec2-aed" \
--per_device_train_batch_size="8" \
--per_device_eval_batch_size="2" \
--learning_rate="1e-4" \
--warmup_steps="500" \
--logging_steps="25" \
--max_steps="50001" \
--eval_steps="10000" \
--save_steps="10000" \
--generation_max_length="40" \
--generation_num_beams="1" \
--final_generation_max_length="250" \
--final_generation_num_beams="12" \
--generation_length_penalty="1.5" \
--hidden_dropout="0.2" \
--activation_dropout="0.2" \
--feat_proj_dropout="0.2" \
--overwrite_output_dir \
--gradient_checkpointing \
--freeze_feature_encoder \
--predict_with_generate \
--do_eval \
--do_train \
--do_predict \
--push_to_hub \
--use_auth_token
```
|