|
#!/usr/bin/env bash |
|
python -m torch.distributed.launch \ |
|
--nproc_per_node 4 run_speech_recognition_ctc_streaming.py \ |
|
--dataset_name="common_voice" \ |
|
--model_name_or_path="facebook/wav2vec2-xls-r-300m" \ |
|
--tokenizer_name_or_path="anton-l/wav2vec2-tokenizer-turkish" \ |
|
--dataset_config_name="tr" \ |
|
--train_split_name="train+validation" \ |
|
--eval_split_name="test" \ |
|
--output_dir="wav2vec2-xls-r-common_voice-tr-ft-stream" \ |
|
--overwrite_output_dir \ |
|
--max_steps="5000" \ |
|
--per_device_train_batch_size="8" \ |
|
--gradient_accumulation_steps="2" \ |
|
--learning_rate="5e-4" \ |
|
--warmup_steps="500" \ |
|
--evaluation_strategy="steps" \ |
|
--text_column_name="sentence" \ |
|
--save_steps="500" \ |
|
--eval_steps="500" \ |
|
--logging_steps="1" \ |
|
--layerdrop="0.0" \ |
|
--eval_metrics wer cer \ |
|
--save_total_limit="1" \ |
|
--mask_time_prob="0.3" \ |
|
--mask_time_length="10" \ |
|
--mask_feature_prob="0.1" \ |
|
--mask_feature_length="64" \ |
|
--freeze_feature_encoder \ |
|
--chars_to_ignore , ? . ! - \; \: \" “ % ‘ ” � \ |
|
--max_duration_in_seconds="20" \ |
|
--shuffle_buffer_size="500" \ |
|
--fp16 \ |
|
--push_to_hub \ |
|
--do_train --do_eval \ |
|
--gradient_checkpointing |
