File size: 3,770 Bytes
55f3766 |
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 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 |
#!/usr/bin/env bash
DATASET_NAMES="distil-whisper/tedlium-long-form+distil-whisper/earnings21+distil-whisper/earnings22+distil-whisper/meanwhile+distil-whisper/rev16"
DATASET_CONFIG_NAMES="all+full+full+default+whisper_subset"
DATASET_SPLIT_NAMES="test+test+test+test+test"
TEXT_COLUMN_NAMES="text+transcription+transcription+text+transcription"
python run_long_form_transcription.py \
--model_name_or_path "openai/whisper-tiny.en" \
--dataset_name $DATASET_NAMES \
--dataset_config_name $DATASET_CONFIG_NAMES \
--dataset_split_name $DATASET_SPLIT_NAMES \
--text_column_name $TEXT_COLUMN_NAMES \
--cache_dir "/home/sanchitgandhi/.cache" \
--dataset_cache_dir "/home/sanchitgandhi/.cache" \
--output_dir "./" \
--wandb_dir "/home/sanchitgandhi/.cache" \
--wandb_project "distil-whisper-long-form-test" \
--wandb_name "tiny.en" \
--per_device_eval_batch_size 16 \
--chunk_length_s 30 \
--generation_max_length 128 \
--dtype "bfloat16" \
--report_to "wandb" \
--streaming \
--return_timestamps
python run_long_form_transcription.py \
--model_name_or_path "openai/whisper-base.en" \
--dataset_name $DATASET_NAMES \
--dataset_config_name $DATASET_CONFIG_NAMES \
--dataset_split_name $DATASET_SPLIT_NAMES \
--text_column_name $TEXT_COLUMN_NAMES \
--cache_dir "/home/sanchitgandhi/.cache" \
--dataset_cache_dir "/home/sanchitgandhi/.cache" \
--output_dir "./" \
--wandb_dir "/home/sanchitgandhi/.cache" \
--wandb_project "distil-whisper-long-form-test" \
--wandb_name "base.en" \
--per_device_eval_batch_size 16 \
--chunk_length_s 30 \
--generation_max_length 128 \
--dtype "bfloat16" \
--report_to "wandb" \
--streaming \
--return_timestamps
python run_long_form_transcription.py \
--model_name_or_path "openai/whisper-small.en" \
--dataset_name $DATASET_NAMES \
--dataset_config_name $DATASET_CONFIG_NAMES \
--dataset_split_name $DATASET_SPLIT_NAMES \
--text_column_name $TEXT_COLUMN_NAMES \
--cache_dir "/home/sanchitgandhi/.cache" \
--dataset_cache_dir "/home/sanchitgandhi/.cache" \
--output_dir "./" \
--wandb_dir "/home/sanchitgandhi/.cache" \
--wandb_project "distil-whisper-long-form-test" \
--wandb_name "small.en" \
--per_device_eval_batch_size 16 \
--chunk_length_s 30 \
--generation_max_length 128 \
--dtype "bfloat16" \
--report_to "wandb" \
--streaming \
--return_timestamps
python run_long_form_transcription.py \
--model_name_or_path "openai/whisper-medium.en" \
--dataset_name $DATASET_NAMES \
--dataset_config_name $DATASET_CONFIG_NAMES \
--dataset_split_name $DATASET_SPLIT_NAMES \
--text_column_name $TEXT_COLUMN_NAMES \
--cache_dir "/home/sanchitgandhi/.cache" \
--dataset_cache_dir "/home/sanchitgandhi/.cache" \
--output_dir "./" \
--wandb_dir "/home/sanchitgandhi/.cache" \
--wandb_project "distil-whisper-long-form-test" \
--wandb_name "medium.en" \
--per_device_eval_batch_size 16 \
--chunk_length_s 30 \
--generation_max_length 128 \
--dtype "bfloat16" \
--report_to "wandb" \
--streaming \
--return_timestamps
python run_long_form_transcription.py \
--model_name_or_path "openai/whisper-large-v2" \
--dataset_name $DATASET_NAMES \
--dataset_config_name $DATASET_CONFIG_NAMES \
--dataset_split_name $DATASET_SPLIT_NAMES \
--text_column_name $TEXT_COLUMN_NAMES \
--cache_dir "/home/sanchitgandhi/.cache" \
--dataset_cache_dir "/home/sanchitgandhi/.cache" \
--output_dir "./" \
--wandb_dir "/home/sanchitgandhi/.cache" \
--wandb_project "distil-whisper-long-form-test" \
--wandb_name "large-v2" \
--per_device_eval_batch_size 16 \
--chunk_length_s 30 \
--generation_max_length 128 \
--dtype "bfloat16" \
--report_to "wandb" \
--streaming \
--return_timestamps
|