PereLluis13 commited on
Commit
5b6412d
1 Parent(s): 65403b6

update model

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ language:
3
+ - ca
4
+ license: apache-2.0
5
+ tags:
6
+ - automatic-speech-recognition
7
+ - mozilla-foundation/common_voice_8_0
8
+ - collectivat/tv3_parla
9
+ - projecte-aina/parlament_parla
10
+ - generated_from_trainer
11
+ - robust-speech-event
12
+ datasets:
13
+ - mozilla-foundation/common_voice_8_0
14
+ - collectivat/tv3_parla
15
+ - projecte-aina/parlament_parla
16
+ model-index:
17
+ - name: wav2vec2-xls-r-1b-ca
18
+ results:
19
+ ---
20
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
21
+ should probably proofread and complete it, then remove this comment. -->
22
+
23
+ # wav2vec2-xls-r-1b-ca
24
+
25
+ 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 - CA dataset.
26
+
27
+ ## Model description
28
+
29
+ Please check the original [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) Model card. This is just a finetuned version of that model.
30
+
31
+ ## Intended uses & limitations
32
+
33
+ As any model trained on crowdsourced data, this model can show the biases and particularities of the data and model used to train this model. Moreover, since this is a speech recognition model, it may underperform for some lower-resourced dialects for the catalan language.
34
+
35
+ ## Training and evaluation data
36
+
37
+ ## Training procedure
38
+
39
+ The data is preprocessed to remove characters not on the catalan alphabet. Moreover, numbers are verbalized using code provided by [@ccoreilly](https://github.com/ccoreilly), which can be found on the text/ folder or [here](https://github.com/CollectivaT-dev/catotron-cpu/blob/master/text/numbers_ca.py).
40
+
41
+ ### Training results
42
+
43
+ Check the Tensorboard tab to check the training profile and evaluation results along training. The model was evaluated on the test splits for each of the datasets used during training.
44
+
45
+ ### Training hyperparameters
46
+
47
+ The following hyperparameters were used during training:
48
+ - learning_rate: 2e-05
49
+ - train_batch_size: 8
50
+ - eval_batch_size: 8
51
+ - seed: 42
52
+ - gradient_accumulation_steps: 8
53
+ - total_train_batch_size: 64
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: linear
56
+ - lr_scheduler_warmup_steps: 2000
57
+ - num_epochs: 10.0
58
+ - mixed_precision_training: Native AMP
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.17.0.dev0
63
+ - Pytorch 1.10.2+cu102
64
+ - Datasets 1.18.3
65
+ - Tokenizers 0.11.0
66
+
67
+ # Thanks
68
+
69
+ Want to thank both [@ccoreilly](https://github.com/ccoreilly) and [@gullabi](https://github.com/gullabi) who have contributed with their own resources and knowledge into making this model possible.
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29986e5b3283319d48ecefdd68fd3bb0fe2061d61358907401c9fdc74053f315
3
  size 3850543281
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:460a907cccb967dcaf1e86c147c373256527b490cd81f16e4118691f11540bc1
3
  size 3850543281
runs/Feb02_22-48-04_job-7083fbbc-ffb8-4f9b-8706-99212ecf5dd3/1643843696.0612628/events.out.tfevents.1643843696.job-7083fbbc-ffb8-4f9b-8706-99212ecf5dd3.34573.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:247990135b2ab8e66109696533617ffee09d3b576aa5b09a97e1e755efea4cb9
3
+ size 4808
runs/Feb02_22-48-04_job-7083fbbc-ffb8-4f9b-8706-99212ecf5dd3/events.out.tfevents.1643843696.job-7083fbbc-ffb8-4f9b-8706-99212ecf5dd3.34573.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be991b3e225de2c0a64b9d2532338398f4e6e63f66a343c0d1e0744f105a9ecd
3
+ size 22862
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}, {"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}]}
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "PereLluis13/wav2vec2-xls-r-1b-ca", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
 
1
+ {"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "wav2vec2-xls-r-1b-ca", "tokenizer_class": "Wav2Vec2CTCTokenizer", "processor_class": "Wav2Vec2ProcessorWithLM"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b4495658d9c79564d9db2345008309646fb4bbe6823c2bc2d99589d4387f305
3
  size 3055
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf5dc7623df5813d5142da994775815df2fb6df73e2e3bae384d6f76b6bfdc81
3
  size 3055