Skip to content
ModelVerifiedExternal
Download

Facebook Mms 1b All Km Indomain20 Withac

This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set: Loss: 0.1921 Wer: 0.1624

Sourcehuggingface.co/Shagufta/facebook-mms-1b-all-km-indomain20-withac/tree/49c0d4d42c1be0e9fdfe5d954732953d9b0dc420
KindOtherBase modelfacebook/mms-1b-allVersionRevision 49c0d4dPublisher@ShaguftaCgrade

Model source

Kind
Other
File size
3.59 GB
Base model
facebook/mms-1b-all
Version
vRevision 49c0d4d
Updated
Oct 3, 2026
Publisher
@Shagufta
Downloads
15
Parameters
1B
Tasks
Video to video
Source
Hugging Face

Source description

facebook-mms-1b-all-km-indomain20-withac

This model is a fine-tuned version of facebook/mms-1b-all on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1921
  • Wer: 0.1624

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: 1.5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 150
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossWer
11.66500.94452002.91651.0
1.98221.88784000.32160.2960
1.44062.83126000.26890.2619
1.27793.77458000.23560.2238
1.11934.717810000.21900.2080
1.04235.661212000.21540.2038
0.94476.604514000.20700.1944
0.86787.547816000.20390.1877
0.84888.491118000.19840.1817
0.77659.434520000.20370.1793
0.741010.377822000.19440.1726
0.700811.321124000.19830.1720
0.700112.264526000.19610.1741
0.655313.207828000.19670.1684
0.646914.151130000.19530.1682
0.627115.094532000.19210.1641
0.619816.037834000.19210.1628
0.643216.982336000.19240.1639
0.626217.925638000.19260.1627
0.592818.868940000.19260.1624
0.589119.812342000.19210.1624
0.589120.042400.19210.1624

Framework versions

  • Transformers 5.9.0
  • Pytorch 2.11.0+cu128
  • Datasets 4.0.0
  • Tokenizers 0.22.2

Sources

1 source
Hugging FacePrimaryVersion 49c0d4d42c1be0e9fdfe5d954732953d9b0dc420
huggingface.co/Shagufta/facebook-mms-1b-all-km-indomain20-withac/tree/49c0d4d42c1be0e9fdfe5d954732953d9b0dc420

Verified Oct 3

Model artifacts

1 artifact

model.safetensors

safetensors · 3.59 GB · SHA-256 6c52cab2dc70…38fc · Hugging Face

Download file

Source excerpts

3 excerpts
ReadmeJul 11huggingface.co/Shagufta/facebook-mms-1b-all-km-indomain20-withac

--- library_name: transformers license: cc-by-nc-4.0 base_model: facebook/mms-1b-all tags: - generated_from_trainer metrics: - wer model-index: - name: facebook-mms-1b-all-km-indomain20-withac 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. --> # facebook-mms-1b-all-km-indomain20-withac This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the None dataset. It achieves the following results on the evaluation set: - Loss: 0.1921 - Wer: 0.1624 ## 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: 1.5e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 16 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 150 - num_epochs: 20 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Wer | |:-------------:|:-------:|:----:|:---------------:|:------:| | 11.6650 | 0.9445 | 200 | 2.9165 | 1.0 | | 1.9822 | 1.8878 | 400 | 0.3216 | 0.2960 | | 1.4406 | 2.8312 | 600 | 0.2689 | 0.2619 | | 1.2779 | 3.7745 | 800 | 0.2356 | 0.2238 | | 1.1193 | 4.7178 | 1000 | 0.2190 | 0.2080 | | 1.0423 | 5.6612 | 1200 | 0.2154 | 0.2038 | | 0.9447 | 6.6045 | 1400 | 0.2070 | 0.1944 | | 0.8678 | 7.5478 | 1600 | 0.2039 | 0.1877 | | 0.8488 | 8.4911 | 1800 | 0.1984 | 0.1817 | | 0.7765 | 9.4345 | 2000 | 0.2037 | 0.1793 | | 0.7410 | 10.3778 | 2200 | 0.1944 | 0.1726 | | 0.7008 | 11.3211 | 2400 | 0.1983 | 0.1720 | | 0.7001 | 12.2645 | 2600 | 0.1961 | 0.1741 | | 0.6553 | 13.2078 | 2800 | 0.1967 | 0.1684 | | 0.6469 | 14.1511 | 3000 | 0.1953 | 0.1682 | | 0.6271 | 15.0945 | 3200 | 0.1921 | 0.1641 | | 0.6198 | 16.0378 | 3400 | 0.1921 | 0.1628 | | 0.6432 | 16.9823 | 3600 | 0.1924 | 0.1639 | | 0.6262 | 17.9256 | 3800 | 0.1926 | 0.1627 | | 0.5928 | 18.8689 | 4000 | 0.1926 | 0.1624 | | 0.5891 | 19.8123 | 4...

NoteOct 3huggingface.co/Shagufta/facebook-mms-1b-all-km-indomain20-withac

Source context: 15 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Shagufta/facebook-mms-1b-all-km-indomain20-withac

NoteJul 17huggingface.co/Shagufta/facebook-mms-1b-all-km-indomain20-withac

Source context: 3 downloads · 0 likes · Pipeline automatic-speech-recognition · Library transformers · Repo Shagufta/facebook-mms-1b-all-km-indomain20-withac