asr-africa
/

wav2vec2-xls-r-300m-CV_Fleurs_AMMI_ALFFA-sw-200hrs-v1

@@ -1,199 +1,164 @@
 ---
 library_name: transformers
-tags: []
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
 library_name: transformers
+license: apache-2.0
+base_model: facebook/wav2vec2-xls-r-300m
+tags:
+- generated_from_trainer
+metrics:
+- wer
+model-index:
+- name: wav2vec2-xls-r-300m-CV_Fleurs_AMMI_ALFFA-sw-200hrs-v1
+  results: []
 ---
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+# wav2vec2-xls-r-300m-CV_Fleurs_AMMI_ALFFA-sw-200hrs-v1
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6946
+- Wer: 0.1373
+- Cer: 0.0454
+## Model description
+More information needed
+## Intended uses & limitations
+More information needed
+## Training and evaluation data
+More information needed
+## Training procedure
+### Training hyperparameters
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 100
+- mixed_precision_training: Native AMP
+### Training results
+| Training Loss | Epoch | Step   | Validation Loss | Wer    | Cer    |
+|:-------------:|:-----:|:------:|:---------------:|:------:|:------:|
+| 1.6189        | 1.0   | 8064   | 0.5376          | 0.4012 | 0.1324 |
+| 0.7423        | 2.0   | 16128  | 0.4487          | 0.2992 | 0.0890 |
+| 0.6218        | 3.0   | 24192  | 0.4022          | 0.2694 | 0.0811 |
+| 0.5548        | 4.0   | 32256  | 0.3769          | 0.2610 | 0.0793 |
+| 0.5081        | 5.0   | 40320  | 0.3396          | 0.2463 | 0.0758 |
+| 0.4712        | 6.0   | 48384  | 0.3460          | 0.2382 | 0.0744 |
+| 0.4421        | 7.0   | 56448  | 0.3419          | 0.2297 | 0.0711 |
+| 0.418         | 8.0   | 64512  | 0.3165          | 0.2230 | 0.0686 |
+| 0.3977        | 9.0   | 72576  | 0.3380          | 0.2389 | 0.0843 |
+| 0.3748        | 10.0  | 80640  | 0.3046          | 0.2174 | 0.0691 |
+| 0.3587        | 11.0  | 88704  | 0.3301          | 0.2114 | 0.0663 |
+| 0.3423        | 12.0  | 96768  | 0.3172          | 0.2048 | 0.0629 |
+| 0.3282        | 13.0  | 104832 | 0.3118          | 0.2056 | 0.0672 |
+| 0.3132        | 14.0  | 112896 | 0.3213          | 0.1971 | 0.0607 |
+| 0.3009        | 15.0  | 120960 | 0.3292          | 0.1926 | 0.0619 |
+| 0.2887        | 16.0  | 129024 | 0.2949          | 0.1963 | 0.0603 |
+| 0.2778        | 17.0  | 137088 | 0.3066          | 0.1884 | 0.0590 |
+| 0.2649        | 18.0  | 145152 | 0.3105          | 0.1883 | 0.0589 |
+| 0.254         | 19.0  | 153216 | 0.3161          | 0.1851 | 0.0583 |
+| 0.2444        | 20.0  | 161280 | 0.3183          | 0.1812 | 0.0567 |
+| 0.2364        | 21.0  | 169344 | 0.3306          | 0.1803 | 0.0579 |
+| 0.2281        | 22.0  | 177408 | 0.3106          | 0.1818 | 0.0573 |
+| 0.219         | 23.0  | 185472 | 0.3367          | 0.1826 | 0.0573 |
+| 0.2102        | 24.0  | 193536 | 0.3485          | 0.1747 | 0.0551 |
+| 0.2027        | 25.0  | 201600 | 0.3619          | 0.1765 | 0.0558 |
+| 0.1962        | 26.0  | 209664 | 0.3609          | 0.1729 | 0.0547 |
+| 0.1907        | 27.0  | 217728 | 0.3344          | 0.1754 | 0.0554 |
+| 0.1839        | 28.0  | 225792 | 0.3001          | 0.1770 | 0.0565 |
+| 0.1784        | 29.0  | 233856 | 0.3524          | 0.1696 | 0.0550 |
+| 0.1727        | 30.0  | 241920 | 0.3270          | 0.1767 | 0.0558 |
+| 0.1653        | 31.0  | 249984 | 0.3251          | 0.1732 | 0.0554 |
+| 0.161         | 32.0  | 258048 | 0.3885          | 0.1672 | 0.0539 |
+| 0.1575        | 33.0  | 266112 | 0.3292          | 0.1675 | 0.0536 |
+| 0.1532        | 34.0  | 274176 | 0.3686          | 0.1682 | 0.0541 |
+| 0.1483        | 35.0  | 282240 | 0.3920          | 0.1641 | 0.0531 |
+| 0.1449        | 36.0  | 290304 | 0.4157          | 0.1626 | 0.0527 |
+| 0.1411        | 37.0  | 298368 | 0.3790          | 0.1706 | 0.0544 |
+| 0.1366        | 38.0  | 306432 | 0.3723          | 0.1690 | 0.0546 |
+| 0.1342        | 39.0  | 314496 | 0.3982          | 0.1645 | 0.0528 |
+| 0.1311        | 40.0  | 322560 | 0.4210          | 0.1623 | 0.0522 |
+| 0.127         | 41.0  | 330624 | 0.3935          | 0.1688 | 0.0541 |
+| 0.1235        | 42.0  | 338688 | 0.3883          | 0.1603 | 0.0516 |
+| 0.1215        | 43.0  | 346752 | 0.4329          | 0.1631 | 0.0521 |
+| 0.1179        | 44.0  | 354816 | 0.3834          | 0.1691 | 0.0554 |
+| 0.1145        | 45.0  | 362880 | 0.3790          | 0.1639 | 0.0523 |
+| 0.1121        | 46.0  | 370944 | 0.4199          | 0.1618 | 0.0520 |
+| 0.1103        | 47.0  | 379008 | 0.4275          | 0.1605 | 0.0516 |
+| 0.1067        | 48.0  | 387072 | 0.4024          | 0.1605 | 0.0520 |
+| 0.1061        | 49.0  | 395136 | 0.4334          | 0.1569 | 0.0516 |
+| 0.1023        | 50.0  | 403200 | 0.4152          | 0.1566 | 0.0509 |
+| 0.0999        | 51.0  | 411264 | 0.4638          | 0.1571 | 0.0509 |
+| 0.0988        | 52.0  | 419328 | 0.4478          | 0.1577 | 0.0512 |
+| 0.0956        | 53.0  | 427392 | 0.4565          | 0.1558 | 0.0505 |
+| 0.0935        | 54.0  | 435456 | 0.4681          | 0.1595 | 0.0514 |
+| 0.0911        | 55.0  | 443520 | 0.4740          | 0.1558 | 0.0503 |
+| 0.0894        | 56.0  | 451584 | 0.4746          | 0.1535 | 0.0500 |
+| 0.0881        | 57.0  | 459648 | 0.4513          | 0.1550 | 0.0503 |
+| 0.0861        | 58.0  | 467712 | 0.5096          | 0.1538 | 0.0498 |
+| 0.0831        | 59.0  | 475776 | 0.4405          | 0.1561 | 0.0509 |
+| 0.0828        | 60.0  | 483840 | 0.4725          | 0.1507 | 0.0492 |
+| 0.0811        | 61.0  | 491904 | 0.4770          | 0.1527 | 0.0500 |
+| 0.079         | 62.0  | 499968 | 0.5079          | 0.1511 | 0.0495 |
+| 0.0767        | 63.0  | 508032 | 0.4888          | 0.1511 | 0.0494 |
+| 0.0752        | 64.0  | 516096 | 0.4707          | 0.1522 | 0.0494 |
+| 0.0737        | 65.0  | 524160 | 0.4891          | 0.1537 | 0.0497 |
+| 0.0721        | 66.0  | 532224 | 0.5608          | 0.1488 | 0.0488 |
+| 0.0701        | 67.0  | 540288 | 0.5018          | 0.1527 | 0.0497 |
+| 0.0685        | 68.0  | 548352 | 0.5504          | 0.1476 | 0.0482 |
+| 0.0675        | 69.0  | 556416 | 0.5235          | 0.1473 | 0.0481 |
+| 0.0652        | 70.0  | 564480 | 0.5468          | 0.1499 | 0.0488 |
+| 0.0634        | 71.0  | 572544 | 0.5204          | 0.1488 | 0.0485 |
+| 0.0623        | 72.0  | 580608 | 0.5535          | 0.1485 | 0.0483 |
+| 0.0617        | 73.0  | 588672 | 0.5842          | 0.1456 | 0.0479 |
+| 0.0598        | 74.0  | 596736 | 0.5706          | 0.1490 | 0.0481 |
+| 0.0582        | 75.0  | 604800 | 0.5647          | 0.1469 | 0.0478 |
+| 0.0568        | 76.0  | 612864 | 0.5678          | 0.1475 | 0.0484 |
+| 0.0558        | 77.0  | 620928 | 0.5805          | 0.1469 | 0.0483 |
+| 0.0549        | 78.0  | 628992 | 0.5655          | 0.1448 | 0.0474 |
+| 0.0538        | 79.0  | 637056 | 0.5573          | 0.1446 | 0.0476 |
+| 0.0524        | 80.0  | 645120 | 0.5953          | 0.1425 | 0.0472 |
+| 0.0514        | 81.0  | 653184 | 0.6070          | 0.1422 | 0.0475 |
+| 0.0503        | 82.0  | 661248 | 0.5991          | 0.1427 | 0.0468 |
+| 0.0496        | 83.0  | 669312 | 0.6211          | 0.1421 | 0.0469 |
+| 0.0479        | 84.0  | 677376 | 0.5988          | 0.1431 | 0.0470 |
+| 0.0458        | 85.0  | 685440 | 0.6471          | 0.1418 | 0.0468 |
+| 0.0463        | 86.0  | 693504 | 0.6437          | 0.1415 | 0.0469 |
+| 0.0447        | 87.0  | 701568 | 0.6472          | 0.1415 | 0.0464 |
+| 0.0449        | 88.0  | 709632 | 0.6418          | 0.1407 | 0.0465 |
+| 0.043         | 89.0  | 717696 | 0.6302          | 0.1391 | 0.0461 |
+| 0.0419        | 90.0  | 725760 | 0.6287          | 0.1417 | 0.0464 |
+| 0.0402        | 91.0  | 733824 | 0.6573          | 0.1404 | 0.0464 |
+| 0.0403        | 92.0  | 741888 | 0.6369          | 0.1397 | 0.0458 |
+| 0.0397        | 93.0  | 749952 | 0.6820          | 0.1391 | 0.0459 |
+| 0.0385        | 94.0  | 758016 | 0.6853          | 0.1380 | 0.0456 |
+| 0.038         | 95.0  | 766080 | 0.6592          | 0.1384 | 0.0459 |
+| 0.0372        | 96.0  | 774144 | 0.6826          | 0.1373 | 0.0454 |
+| 0.0361        | 97.0  | 782208 | 0.6724          | 0.1371 | 0.0456 |
+| 0.0355        | 98.0  | 790272 | 0.6876          | 0.1372 | 0.0455 |
+| 0.0354        | 99.0  | 798336 | 0.6837          | 0.1372 | 0.0454 |
+| 0.0354        | 100.0 | 806400 | 0.6946          | 0.1373 | 0.0454 |
+### Framework versions
+- Transformers 4.46.1
+- Pytorch 2.1.0+cu118
+- Datasets 3.1.0
+- Tokenizers 0.20.1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af861095f3e1d93082684eea941cfd737ed918577bc053198c637ae23c161f08
 size 1262082180

 version https://git-lfs.github.com/spec/v1
+oid sha256:90c179c42c18d8d7ec850d1e96215883a2a8bfe9bf348686a1da92200f8818c5
 size 1262082180