Model save

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: qanastek/whisper-base-french-cased
+tags:
+- generated_from_trainer
+datasets:
+- fleurs
+metrics:
+- wer
+model-index:
+- name: qanastek/whisper-base-french-cased
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: fleurs
+      type: fleurs
+      config: fr_fr
+      split: test
+      args: fr_fr
+    metrics:
+    - name: Wer
+      type: wer
+      value: 23.795498749652683
+---
+
+<!-- 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. -->
+
+# qanastek/whisper-base-french-cased
+
+This model is a fine-tuned version of [qanastek/whisper-base-french-cased](https://huggingface.co/qanastek/whisper-base-french-cased) on the fleurs dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5395
+- Wer: 23.7955
+
+## 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-07
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- training_steps: 5000
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Wer     |
+|:-------------:|:------:|:----:|:---------------:|:-------:|
+| 0.3835        | 105.26 | 1000 | 0.5892          | 25.4237 |
+| 0.2837        | 210.53 | 2000 | 0.5526          | 23.8955 |
+| 0.2323        | 315.79 | 3000 | 0.5432          | 24.0122 |
+| 0.1961        | 421.05 | 4000 | 0.5402          | 23.7955 |
+| 0.1863        | 526.32 | 5000 | 0.5395          | 23.7955 |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.2.dev0
+- Tokenizers 0.15.0

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50257,
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:378161b6d9d35d4137105bd7e3a33fd4acd3b97c586d8d75c9944a4c6e733e19
+oid sha256:2e505d1c135dd0119375f3b642a5d470fc3bd1f7802735d0507d4b91d8f0297a
 size 290403936