Model save

README.md

@@ -0,0 +1,84 @@
+---
+license: cc-by-nc-4.0
+base_model: facebook/mms-1b-all
+tags:
+- generated_from_trainer
+datasets:
+- common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: model_mms
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: common_voice_11_0
+      config: tr
+      split: test[:10]
+      args: tr
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.44285714285714284
+---
+
+<!-- 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. -->
+
+# model_mms
+
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4310
+- Wer: 0.4429
+
+## 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: 0.001
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer    |
+|:-------------:|:-----:|:----:|:---------------:|:------:|
+| 0.2499        | 0.12  | 100  | 0.4539          | 0.4714 |
+| 0.2405        | 0.25  | 200  | 0.4487          | 0.4429 |
+| 0.235         | 0.37  | 300  | 0.4289          | 0.4143 |
+| 0.2432        | 0.49  | 400  | 0.4239          | 0.4    |
+| 0.2373        | 0.61  | 500  | 0.4380          | 0.4429 |
+| 0.2341        | 0.74  | 600  | 0.4435          | 0.4286 |
+| 0.2333        | 0.86  | 700  | 0.4459          | 0.4429 |
+| 0.2348        | 0.98  | 800  | 0.4310          | 0.4429 |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ad6edb5e6217819e79f55197c82721fd73712546aafa868d34be1e9fdde328f
+oid sha256:9d9a5a23a2f0c1f069ab54a932a2d0a537867bd21169ef5e9be8c530e45f5337
 size 3858942164

runs/Jan11_11-39-21_76f6f48fe926/events.out.tfevents.1704973807.76f6f48fe926.1646.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4308ba5372f9391beb8263f17de52654aa7ab3dc1ea5a2f6193aa723816aa371
-size 8641
+oid sha256:d6cd96067c54f95f5cc2a5d86e47f5a9e204a505bb5a3a962a68c9c35fc0cfb8
+size 9945