sulaimank
/

wav2vec-xlsr-grain-lg_cv_only

@@ -1,199 +1,179 @@
 ---
 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
+datasets:
+- common_voice_17_0
+metrics:
+- wer
+model-index:
+- name: wav2vec-xlsr-grain-lg_cv_only
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_17_0
+      type: common_voice_17_0
+      config: lg
+      split: test[:10%]
+      args: lg
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.22608421715845847
 ---
+<!-- 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. -->
+# wav2vec-xlsr-grain-lg_cv_only
+This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice_17_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7249
+- Wer: 0.2261
+- Cer: 0.0663
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- 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    |
+|:-------------:|:-----:|:------:|:---------------:|:------:|:------:|
+| 1.7903        | 1.0   | 2221   | 0.4623          | 0.4252 | 0.1113 |
+| 0.6251        | 2.0   | 4442   | 0.4990          | 0.3665 | 0.1008 |
+| 0.528         | 3.0   | 6663   | 0.3703          | 0.3417 | 0.0958 |
+| 0.4766        | 4.0   | 8884   | 0.3617          | 0.3209 | 0.0899 |
+| 0.4419        | 5.0   | 11105  | 0.3458          | 0.3002 | 0.0853 |
+| 0.4112        | 6.0   | 13326  | 0.3946          | 0.3075 | 0.0856 |
+| 0.3909        | 7.0   | 15547  | 0.3615          | 0.2984 | 0.0854 |
+| 0.3714        | 8.0   | 17768  | 0.3903          | 0.2916 | 0.0820 |
+| 0.3537        | 9.0   | 19989  | 0.4078          | 0.2935 | 0.0829 |
+| 0.3375        | 10.0  | 22210  | 0.3634          | 0.2886 | 0.0849 |
+| 0.3205        | 11.0  | 24431  | 0.3772          | 0.2892 | 0.0801 |
+| 0.307         | 12.0  | 26652  | 0.3912          | 0.2810 | 0.0785 |
+| 0.2961        | 13.0  | 28873  | 0.3527          | 0.2801 | 0.0803 |
+| 0.2833        | 14.0  | 31094  | 0.3524          | 0.2892 | 0.0824 |
+| 0.272         | 15.0  | 33315  | 0.3955          | 0.2834 | 0.0809 |
+| 0.2608        | 16.0  | 35536  | 0.3707          | 0.2805 | 0.0799 |
+| 0.2524        | 17.0  | 37757  | 0.4076          | 0.2834 | 0.0792 |
+| 0.2445        | 18.0  | 39978  | 0.4205          | 0.2768 | 0.0790 |
+| 0.2304        | 19.0  | 42199  | 0.4796          | 0.2809 | 0.0802 |
+| 0.2266        | 20.0  | 44420  | 0.3985          | 0.2768 | 0.0799 |
+| 0.2154        | 21.0  | 46641  | 0.4254          | 0.2748 | 0.0788 |
+| 0.2098        | 22.0  | 48862  | 0.4124          | 0.2703 | 0.0776 |
+| 0.1972        | 23.0  | 51083  | 0.3918          | 0.2728 | 0.0783 |
+| 0.1925        | 24.0  | 53304  | 0.4703          | 0.2707 | 0.0783 |
+| 0.1842        | 25.0  | 55525  | 0.4228          | 0.2724 | 0.0786 |
+| 0.1775        | 26.0  | 57746  | 0.4272          | 0.2765 | 0.0784 |
+| 0.1729        | 27.0  | 59967  | 0.4161          | 0.2729 | 0.0780 |
+| 0.1656        | 28.0  | 62188  | 0.4232          | 0.2648 | 0.0777 |
+| 0.1565        | 29.0  | 64409  | 0.4187          | 0.2691 | 0.0780 |
+| 0.1555        | 30.0  | 66630  | 0.4280          | 0.2609 | 0.0757 |
+| 0.148         | 31.0  | 68851  | 0.4350          | 0.2669 | 0.0778 |
+| 0.1443        | 32.0  | 71072  | 0.4718          | 0.2676 | 0.0782 |
+| 0.1407        | 33.0  | 73293  | 0.4996          | 0.2723 | 0.0768 |
+| 0.1366        | 34.0  | 75514  | 0.4620          | 0.2701 | 0.0770 |
+| 0.1321        | 35.0  | 77735  | 0.5067          | 0.2691 | 0.0762 |
+| 0.1288        | 36.0  | 79956  | 0.4975          | 0.2613 | 0.0747 |
+| 0.1273        | 37.0  | 82177  | 0.4832          | 0.2584 | 0.0744 |
+| 0.1218        | 38.0  | 84398  | 0.5097          | 0.2587 | 0.0759 |
+| 0.1183        | 39.0  | 86619  | 0.5145          | 0.2657 | 0.0759 |
+| 0.1174        | 40.0  | 88840  | 0.5500          | 0.2599 | 0.0753 |
+| 0.1142        | 41.0  | 91061  | 0.5112          | 0.2674 | 0.0761 |
+| 0.1107        | 42.0  | 93282  | 0.5121          | 0.2615 | 0.0745 |
+| 0.1088        | 43.0  | 95503  | 0.5215          | 0.2605 | 0.0753 |
+| 0.1056        | 44.0  | 97724  | 0.4900          | 0.2548 | 0.0735 |
+| 0.1046        | 45.0  | 99945  | 0.4887          | 0.2565 | 0.0729 |
+| 0.1027        | 46.0  | 102166 | 0.5140          | 0.2480 | 0.0712 |
+| 0.0995        | 47.0  | 104387 | 0.5110          | 0.2552 | 0.0726 |
+| 0.0967        | 48.0  | 106608 | 0.5228          | 0.2562 | 0.0731 |
+| 0.0938        | 49.0  | 108829 | 0.4963          | 0.2464 | 0.0702 |
+| 0.0934        | 50.0  | 111050 | 0.5024          | 0.2496 | 0.0710 |
+| 0.0898        | 51.0  | 113271 | 0.6114          | 0.2563 | 0.0747 |
+| 0.0891        | 52.0  | 115492 | 0.5993          | 0.2575 | 0.0728 |
+| 0.0864        | 53.0  | 117713 | 0.6181          | 0.2517 | 0.0721 |
+| 0.0849        | 54.0  | 119934 | 0.7066          | 0.2550 | 0.0739 |
+| 0.0829        | 55.0  | 122155 | 0.5745          | 0.2491 | 0.0720 |
+| 0.0811        | 56.0  | 124376 | 0.5194          | 0.2438 | 0.0701 |
+| 0.0804        | 57.0  | 126597 | 0.6308          | 0.2474 | 0.0716 |
+| 0.0773        | 58.0  | 128818 | 0.5573          | 0.2428 | 0.0698 |
+| 0.076         | 59.0  | 131039 | 0.5476          | 0.2462 | 0.0708 |
+| 0.0748        | 60.0  | 133260 | 0.5976          | 0.2440 | 0.0717 |
+| 0.0742        | 61.0  | 135481 | 0.6067          | 0.2448 | 0.0714 |
+| 0.0725        | 62.0  | 137702 | 0.5574          | 0.2439 | 0.0702 |
+| 0.0711        | 63.0  | 139923 | 0.5936          | 0.2409 | 0.0711 |
+| 0.0698        | 64.0  | 142144 | 0.6039          | 0.2385 | 0.0715 |
+| 0.0683        | 65.0  | 144365 | 0.5694          | 0.2417 | 0.0716 |
+| 0.066         | 66.0  | 146586 | 0.6021          | 0.2415 | 0.0701 |
+| 0.0653        | 67.0  | 148807 | 0.5839          | 0.2428 | 0.0702 |
+| 0.0633        | 68.0  | 151028 | 0.5638          | 0.2353 | 0.0678 |
+| 0.0621        | 69.0  | 153249 | 0.5731          | 0.2412 | 0.0696 |
+| 0.0613        | 70.0  | 155470 | 0.6641          | 0.2430 | 0.0713 |
+| 0.0606        | 71.0  | 157691 | 0.5871          | 0.2396 | 0.0693 |
+| 0.0576        | 72.0  | 159912 | 0.6178          | 0.2424 | 0.0708 |
+| 0.057         | 73.0  | 162133 | 0.6113          | 0.2356 | 0.0680 |
+| 0.0558        | 74.0  | 164354 | 0.5890          | 0.2328 | 0.0683 |
+| 0.0555        | 75.0  | 166575 | 0.6186          | 0.2427 | 0.0701 |
+| 0.0542        | 76.0  | 168796 | 0.6637          | 0.2438 | 0.0709 |
+| 0.0526        | 77.0  | 171017 | 0.6172          | 0.2449 | 0.0701 |
+| 0.0519        | 78.0  | 173238 | 0.6267          | 0.2384 | 0.0710 |
+| 0.0505        | 79.0  | 175459 | 0.6162          | 0.2366 | 0.0681 |
+| 0.0494        | 80.0  | 177680 | 0.6146          | 0.2396 | 0.0688 |
+| 0.0486        | 81.0  | 179901 | 0.5919          | 0.2316 | 0.0678 |
+| 0.0482        | 82.0  | 182122 | 0.6668          | 0.2363 | 0.0716 |
+| 0.0467        | 83.0  | 184343 | 0.6901          | 0.2288 | 0.0682 |
+| 0.0457        | 84.0  | 186564 | 0.6474          | 0.2365 | 0.0688 |
+| 0.0452        | 85.0  | 188785 | 0.6615          | 0.2352 | 0.0697 |
+| 0.0434        | 86.0  | 191006 | 0.6998          | 0.2311 | 0.0683 |
+| 0.0423        | 87.0  | 193227 | 0.6605          | 0.2279 | 0.0674 |
+| 0.0423        | 88.0  | 195448 | 0.7154          | 0.2361 | 0.0709 |
+| 0.0408        | 89.0  | 197669 | 0.6706          | 0.2260 | 0.0658 |
+| 0.041         | 90.0  | 199890 | 0.7034          | 0.2263 | 0.0668 |
+| 0.0391        | 91.0  | 202111 | 0.6943          | 0.2258 | 0.0659 |
+| 0.0387        | 92.0  | 204332 | 0.6964          | 0.2259 | 0.0660 |
+| 0.0378        | 93.0  | 206553 | 0.6930          | 0.2278 | 0.0661 |
+| 0.0368        | 94.0  | 208774 | 0.7106          | 0.2247 | 0.0661 |
+| 0.0372        | 95.0  | 210995 | 0.7001          | 0.2245 | 0.0656 |
+| 0.0366        | 96.0  | 213216 | 0.7010          | 0.2247 | 0.0658 |
+| 0.0357        | 97.0  | 215437 | 0.7196          | 0.2228 | 0.0661 |
+| 0.0351        | 98.0  | 217658 | 0.7143          | 0.2238 | 0.0657 |
+| 0.0356        | 99.0  | 219879 | 0.7230          | 0.2262 | 0.0662 |
+| 0.0352        | 100.0 | 222100 | 0.7249          | 0.2261 | 0.0663 |
+### 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 sha256:9256095cf6d06d486c6bfb5117c85fb308351502d8cbf7d67d4781213869d3d4
 size 1261967380

 version https://git-lfs.github.com/spec/v1
+oid sha256:bfdd2dc19990652c3ddab425d2f2a8da93736db69ffdd83bf07938ada50b704e
 size 1261967380