patrickvonplaten
commited on
Commit
•
b1cfea7
1
Parent(s):
469d0a8
End of training
Browse files- all_results.json +8 -0
- config.json +1 -1
- eval_results.json +8 -0
- run.sh +5 -2
- special_tokens_map.json +14 -0
- training_args.bin +1 -1
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_loss": 1.9236905574798584,
|
3 |
+
"eval_runtime": 195.9345,
|
4 |
+
"eval_samples": 12383,
|
5 |
+
"eval_samples_per_second": 63.2,
|
6 |
+
"eval_steps_per_second": 0.99,
|
7 |
+
"eval_wer": 0.9622266612831247
|
8 |
+
}
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./",
|
3 |
"activation_dropout": 0.0,
|
4 |
"adapter_kernel_size": 3,
|
5 |
"adapter_stride": 2,
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_loss": 1.9236905574798584,
|
3 |
+
"eval_runtime": 195.9345,
|
4 |
+
"eval_samples": 12383,
|
5 |
+
"eval_samples_per_second": 63.2,
|
6 |
+
"eval_steps_per_second": 0.99,
|
7 |
+
"eval_wer": 0.9622266612831247
|
8 |
+
}
|
run.sh
CHANGED
@@ -1,11 +1,14 @@
|
|
1 |
#!/usr/bin/env bash
|
|
|
|
|
2 |
python -m torch.distributed.launch \
|
3 |
--nproc_per_node 2 run_speech_recognition_ctc.py \
|
4 |
--dataset_name="/home/patrick_huggingface_co/ami-ihm-kaldi-chunked" \
|
5 |
-
--model_name_or_path="
|
6 |
--dataset_config_name="ihm" \
|
7 |
--train_split_name="train" \
|
8 |
--eval_split_name="validation" \
|
|
|
9 |
--output_dir="./" \
|
10 |
--preprocessing_num_workers="16" \
|
11 |
--overwrite_output_dir \
|
@@ -29,4 +32,4 @@ python -m torch.distributed.launch \
|
|
29 |
--fp16 \
|
30 |
--group_by_length \
|
31 |
--push_to_hub \
|
32 |
-
--
|
|
|
1 |
#!/usr/bin/env bash
|
2 |
+
# --do_train --do_eval
|
3 |
+
# --model_name_or_path="facebook/wav2vec2-large-lv60" \
|
4 |
python -m torch.distributed.launch \
|
5 |
--nproc_per_node 2 run_speech_recognition_ctc.py \
|
6 |
--dataset_name="/home/patrick_huggingface_co/ami-ihm-kaldi-chunked" \
|
7 |
+
--model_name_or_path="./" \
|
8 |
--dataset_config_name="ihm" \
|
9 |
--train_split_name="train" \
|
10 |
--eval_split_name="validation" \
|
11 |
+
--tokenizer_name_or_path="./" \
|
12 |
--output_dir="./" \
|
13 |
--preprocessing_num_workers="16" \
|
14 |
--overwrite_output_dir \
|
|
|
32 |
--fp16 \
|
33 |
--group_by_length \
|
34 |
--push_to_hub \
|
35 |
+
--do_eval \
|
special_tokens_map.json
CHANGED
@@ -35,6 +35,20 @@
|
|
35 |
"rstrip": false,
|
36 |
"single_word": false
|
37 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
38 |
{
|
39 |
"content": "</s>",
|
40 |
"lstrip": false,
|
|
|
35 |
"rstrip": false,
|
36 |
"single_word": false
|
37 |
},
|
38 |
+
{
|
39 |
+
"content": "</s>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"content": "<s>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
{
|
53 |
"content": "</s>",
|
54 |
"lstrip": false,
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3311
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2471900d020cb0facb88b64033bf87890f5f59b03f415188f5c601a6e97f49a0
|
3 |
size 3311
|