Plim commited on
Commit
39a2094
β€’
1 Parent(s): 5c2523c

update model card README.md

Browse files
README.md CHANGED
@@ -1,48 +1,32 @@
1
  ---
2
- language:
3
- - fr
4
- license: apache-2.0
5
  tags:
6
- - automatic-speech-recognition
7
- - mozilla-foundation/common_voice_8_0
8
  - generated_from_trainer
9
- - robust-speech-event
10
  model-index:
11
- - name: XLS-R-1B - French
12
- results:
13
- - task:
14
- name: Automatic Speech Recognition
15
- type: automatic-speech-recognition
16
- dataset:
17
- name: Common Voice 8
18
- type: mozilla-foundation/common_voice_8_0
19
- args: fr
20
- metrics:
21
- - name: Test WER
22
- type: wer
23
- value: 18.33
24
- - name: Test CER
25
- type: cer
26
- value: 5.60
27
- - task:
28
- name: Automatic Speech Recognition
29
- type: automatic-speech-recognition
30
- dataset:
31
- name: Robust Speech Event - Dev Data
32
- type: speech-recognition-community-v2/dev_data
33
- args: fr
34
- metrics:
35
- - name: Test WER
36
- type: wer
37
- value: 60.25
38
- - name: Test CER
39
- type: cer
40
- value: 15.68
41
  ---
42
 
 
 
 
 
 
 
 
 
 
 
43
  ## Model description
44
 
45
- This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FR dataset.
 
 
 
 
 
 
 
 
46
 
47
  ## Training procedure
48
 
@@ -58,7 +42,7 @@ The following hyperparameters were used during training:
58
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
59
  - lr_scheduler_type: linear
60
  - lr_scheduler_warmup_steps: 2000
61
- - num_epochs: 4.0
62
  - mixed_precision_training: Native AMP
63
 
64
  ### Training results
@@ -78,11 +62,14 @@ The following hyperparameters were used during training:
78
  | 0.8156 | 3.15 | 11000 | inf | 0.1936 |
79
  | 0.8015 | 3.44 | 12000 | inf | 0.1880 |
80
  | 0.774 | 3.73 | 13000 | inf | 0.1834 |
 
 
 
 
 
 
 
81
 
82
- It achieves the best result on the validation set on STEP 13000:
83
- - Wer: 0.1834
84
-
85
- Some problem occurs when calculating the validation loss.
86
 
87
  ### Framework versions
88
 
@@ -90,16 +77,3 @@ Some problem occurs when calculating the validation loss.
90
  - Pytorch 1.10.2+cu102
91
  - Datasets 1.18.3.dev0
92
  - Tokenizers 0.11.0
93
-
94
- ### Evaluation Commands
95
- 1. To evaluate on `mozilla-foundation/common_voice_8` with split `test`
96
-
97
- ```bash
98
- python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset mozilla-foundation/common_voice_8_0 --config fr --split test
99
- ```
100
-
101
- 2. To evaluate on `speech-recognition-community-v2/dev_data`
102
-
103
- ```bash
104
- python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0
105
- ```
 
1
  ---
 
 
 
2
  tags:
 
 
3
  - generated_from_trainer
 
4
  model-index:
5
+ - name: ''
6
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
10
+ should probably proofread and complete it, then remove this comment. -->
11
+
12
+ #
13
+
14
+ This model is a fine-tuned version of [./checkpoint-13000](https://huggingface.co/./checkpoint-13000) on the None dataset.
15
+ It achieves the following results on the evaluation set:
16
+ - Loss: inf
17
+ - Wer: 0.1854
18
+
19
  ## Model description
20
 
21
+ More information needed
22
+
23
+ ## Intended uses & limitations
24
+
25
+ More information needed
26
+
27
+ ## Training and evaluation data
28
+
29
+ More information needed
30
 
31
  ## Training procedure
32
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 2000
45
+ - num_epochs: 6.0
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
 
62
  | 0.8156 | 3.15 | 11000 | inf | 0.1936 |
63
  | 0.8015 | 3.44 | 12000 | inf | 0.1880 |
64
  | 0.774 | 3.73 | 13000 | inf | 0.1834 |
65
+ | 0.8372 | 4.01 | 14000 | inf | 0.1934 |
66
+ | 0.8075 | 4.3 | 15000 | inf | 0.1923 |
67
+ | 0.8069 | 4.59 | 16000 | inf | 0.1877 |
68
+ | 0.8064 | 4.87 | 17000 | inf | 0.1955 |
69
+ | 0.801 | 5.16 | 18000 | inf | 0.1891 |
70
+ | 0.8022 | 5.45 | 19000 | inf | 0.1895 |
71
+ | 0.792 | 5.73 | 20000 | inf | 0.1854 |
72
 
 
 
 
 
73
 
74
  ### Framework versions
75
 
 
77
  - Pytorch 1.10.2+cu102
78
  - Datasets 1.18.3.dev0
79
  - Tokenizers 0.11.0
 
 
 
 
 
 
 
 
 
 
 
 
 
wandb/run-20220206_201634-uhiy9e2t/files/output.log CHANGED
@@ -11355,3 +11355,17 @@ Configuration saved in ./preprocessor_config.json
11355
  Saving model checkpoint to ./
11356
  Configuration saved in ./config.json
11357
  Model weights saved in ./pytorch_model.bin
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
11355
  Saving model checkpoint to ./
11356
  Configuration saved in ./config.json
11357
  Model weights saved in ./pytorch_model.bin
11358
+ Configuration saved in ./preprocessor_config.json
11359
+ Several commits (2) will be pushed upstream.
11360
+ The progress bars may be unreliable.
11361
+ 02/08/2022 03:24:48 - WARNING - huggingface_hub.repository - Several commits (2) will be pushed upstream.
11362
+ 02/08/2022 03:24:48 - WARNING - huggingface_hub.repository - The progress bars may be unreliable.
11363
+
11364
+
11365
+
11366
+ Upload file wandb/run-20220206_201634-uhiy9e2t/run-uhiy9e2t.wandb: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 114M/117M [00:06<00:00, 21.0MB/s]
11367
+ 02/08/2022 03:24:58 - WARNING - huggingface_hub.repository - To https://huggingface.co/Plim/xls-r-1b-cv_8-fr
11368
+ Upload file wandb/run-20220206_201634-uhiy9e2t/run-uhiy9e2t.wandb: 98%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–Ž | 114M/117M [00:06<00:00, 21.0MB/s]To https://huggingface.co/Plim/xls-r-1b-cv_8-fr
11369
+ 89ae304..5c2523c main -> main
11370
+ Upload file wandb/run-20220206_201634-uhiy9e2t/run-uhiy9e2t.wandb: 100%|β–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆβ–ˆ| 117M/117M [00:08<00:00, 15.1MB/s]
11371
+ Dropping the following result as it does not have all the necessary fields:
wandb/run-20220206_201634-uhiy9e2t/logs/debug-internal.log CHANGED
@@ -32484,3 +32484,15 @@ requests.exceptions.HTTPError: 500 Server Error: Internal Server Error for url:
32484
  2022-02-08 03:24:36,740 DEBUG HandlerThread:10249 [handler.py:handle_request():131] handle_request: stop_status
32485
  2022-02-08 03:24:36,741 DEBUG SenderThread:10249 [sender.py:send_request():249] send_request: stop_status
32486
  2022-02-08 03:24:39,519 DEBUG SenderThread:10249 [sender.py:send():235] send: stats
 
 
 
 
 
 
 
 
 
 
 
 
 
32484
  2022-02-08 03:24:36,740 DEBUG HandlerThread:10249 [handler.py:handle_request():131] handle_request: stop_status
32485
  2022-02-08 03:24:36,741 DEBUG SenderThread:10249 [sender.py:send_request():249] send_request: stop_status
32486
  2022-02-08 03:24:39,519 DEBUG SenderThread:10249 [sender.py:send():235] send: stats
32487
+ 2022-02-08 03:24:51,012 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32488
+ 2022-02-08 03:24:51,911 DEBUG HandlerThread:10249 [handler.py:handle_request():131] handle_request: stop_status
32489
+ 2022-02-08 03:24:51,912 DEBUG SenderThread:10249 [sender.py:send_request():249] send_request: stop_status
32490
+ 2022-02-08 03:24:53,013 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32491
+ 2022-02-08 03:24:55,014 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32492
+ 2022-02-08 03:24:57,016 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32493
+ 2022-02-08 03:24:59,017 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32494
+ 2022-02-08 03:25:01,018 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32495
+ 2022-02-08 03:25:05,021 INFO Thread-8 :10249 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-1b-cv_8-fr/wandb/run-20220206_201634-uhiy9e2t/files/output.log
32496
+ 2022-02-08 03:25:07,248 DEBUG HandlerThread:10249 [handler.py:handle_request():131] handle_request: stop_status
32497
+ 2022-02-08 03:25:07,248 DEBUG SenderThread:10249 [sender.py:send_request():249] send_request: stop_status
32498
+ 2022-02-08 03:25:09,751 DEBUG SenderThread:10249 [sender.py:send():235] send: stats
wandb/run-20220206_201634-uhiy9e2t/run-uhiy9e2t.wandb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b990101dc5be3963b20992a79f5b2fa802fc6f88d9fb12ceade05980531d5087
3
- size 123073975
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:160673feed9ea3ddc328247490fe7d2950cd358fb40b4b827edc8123c80ab0af
3
+ size 123076744