pere commited on
Commit
cf9ffc9
1 Parent(s): 279952e

manual update of training

Browse files
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "facebook/wav2vec2-xls-r-300m",
3
  "activation_dropout": 0.1,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
 
1
  {
2
+ "_name_or_path": "./",
3
  "activation_dropout": 0.1,
4
  "adapter_kernel_size": 3,
5
  "adapter_stride": 2,
run_recover.sh ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ python run_speech_recognition_ctc_bnb.py \
2
+ --dataset_name="NbAiLab/NPSC" \
3
+ --dataset_config_name="16K_mp3" \
4
+ --text_column_name="text" \
5
+ --model_name_or_path="./" \
6
+ --preprocessing_num_workers="8" \
7
+ --output_dir="./" \
8
+ --overwrite_output_dir \
9
+ --hub_model_id="NbAiLab/wav2vec2-xlsr-300m-norwegian" \
10
+ --num_train_epochs="20" \
11
+ --per_device_train_batch_size="16" \
12
+ --per_device_eval_batch_size="16" \
13
+ --gradient_accumulation_steps="16" \
14
+ --learning_rate="7.5e-5" \
15
+ --warmup_steps="0" \
16
+ --evaluation_strategy="steps" \
17
+ --length_column_name="input_length" \
18
+ --chars_to_ignore , ? . ! \- \; \: \" " % ‘ " � — ’ … – \
19
+ --save_steps="500" \
20
+ --eval_steps="500" \
21
+ --logging_steps="100" \
22
+ --layerdrop="0.0" \
23
+ --activation_dropout="0.1" \
24
+ --save_total_limit="3" \
25
+ --freeze_feature_encoder \
26
+ --feat_proj_dropout="0.0" \
27
+ --mask_time_prob="0.75" \
28
+ --mask_time_length="10" \
29
+ --mask_feature_prob="0.25" \
30
+ --mask_feature_length="64" \
31
+ --gradient_checkpointing \
32
+ --use_auth_token \
33
+ --fp16 \
34
+ --group_by_length \
35
+ --do_train --do_eval \
36
+ --max_eval_samples="1000" \
37
+ --push_to_hub
runs/Jan28_11-14-14_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/1643368546.274217/events.out.tfevents.1643368546.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.62563.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4060321ab6f899829a9967df376a1c91f2023b36714fb0a594b0d6ae8d241fe1
3
+ size 4785
runs/Jan28_11-14-14_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/events.out.tfevents.1643368546.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.62563.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44d52227cf0e11e15f17dd279bd817cdbbbfd2cc17a9de4b4bc6ab69207dad57
3
+ size 4682
runs/Jan28_11-22-45_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/1643369035.747634/events.out.tfevents.1643369035.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.68110.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a304a5d832a9156525de136b77999d6d2a0679e412643efab68b09712f52b0c5
3
+ size 4785
runs/Jan28_11-22-45_job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba/events.out.tfevents.1643369035.job-c93f32d8-97c5-48e7-b5ec-c6c950f627ba.68110.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0eaedf3960949bd390f2e65237cf252514e32b567edf341bd347c717e951fb
3
+ size 4993
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}