Training in progress, step 10

README.md

@@ -1,12 +1,81 @@
----
-license: cc-by-nc-sa-4.0
-datasets:
-- mozilla-foundation/common_voice_11_0
-- shadow-wxh/VoiceCommandAudio
-language:
-- de
-- en
-- zh
-metrics:
-- wer
----
+---
+language:
+- de
+license: apache-2.0
+base_model: bofenghuang/whisper-medium-cv11-german
+tags:
+- generated_from_trainer
+datasets:
+- shadow-wxh/VoiceCommandAudio
+metrics:
+- wer
+model-index:
+- name: voicecommand-german-medium
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: VoiceCommandAudio
+      type: shadow-wxh/VoiceCommandAudio
+      args: 'config: de, split: test'
+    metrics:
+    - name: Wer
+      type: wer
+      value: 0.0
+---
+
+<!-- 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. -->
+
+# voicecommand-german-medium
+
+This model is a fine-tuned version of [bofenghuang/whisper-medium-cv11-german](https://huggingface.co/bofenghuang/whisper-medium-cv11-german) on the VoiceCommandAudio dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0011
+- Wer: 0.0
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- training_steps: 30
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 1.2529        | 0.5556 | 10   | 0.3307          | 38.1333 |
+| 0.108         | 1.1111 | 20   | 0.0028          | 0.0     |
+| 0.0026        | 1.6667 | 30   | 0.0011          | 0.0     |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.4.0+cu124
+- Datasets 2.20.0
+- Tokenizers 0.19.1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36addb1c34784f845f7c91ab9389470df0e1d87bbc3622cf93df19326ecb59a7
+oid sha256:2cf5b3f214b8228b05644efb89078961ebb7b7abbea3ed3a85dc1addf60de38e
 size 3055544304

runs/Aug02_19-26-20_DESKTOP-G9B0LHL/events.out.tfevents.1722597984.DESKTOP-G9B0LHL.49188.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29614f378ab304d70bbc31331f500ebdd59050990b3e279e9bdde5ea7a307799
-size 6287
+oid sha256:db062c87a14d5219cc1d2970dea7825a7c2e66aa4bfe79e48bc615f83e881309
+size 7673

runs/Aug05_15-42-12_DESKTOP-G9B0LHL/events.out.tfevents.1722843758.DESKTOP-G9B0LHL.74640.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6629c31e930e1a7836298e6f6934d404adf2c12aa85a2a9fb18bf2dccf345f43
+size 6287

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf3edfdf27870aaa122661d848bf3753cb1c32704b042e05eab48b3bb272f30f
+oid sha256:ecaea1d5b9933c3a3c3ebebffdf652f4fc6b7478c2811e9978670f57c83787ef
 size 5368