RafatK/Azerbaijani_whisper

README.md

@@ -16,15 +16,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.3327
-- eval_cer: 5.4203
-- eval_wer: 20.4638
-- eval_bleu: 0.6173
-- eval_runtime: 1022.0953
-- eval_samples_per_second: 0.898
-- eval_steps_per_second: 0.225
-- epoch: 0.2134
-- step: 1000
+- eval_loss: 0.2553
+- eval_cer: 3.9437
+- eval_wer: 13.3115
+- eval_bleu: 0.7447
+- eval_runtime: 981.1698
+- eval_samples_per_second: 0.936
+- eval_steps_per_second: 0.234
+- epoch: 0.96
+- step: 4500
 
 ## Model description
 
@@ -52,12 +52,12 @@ The following hyperparameters were used during training:
 - 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
 - lr_scheduler_warmup_steps: 2
-- training_steps: 9500
+- training_steps: 10500
 - mixed_precision_training: Native AMP
 
 ### Framework versions
 
-- Transformers 4.48.0
+- Transformers 4.52.0
 - Pytorch 2.9.1+cu126
 - Datasets 3.6.0
 - Tokenizers 0.21.4

config.json

@@ -1,5 +1,4 @@
 {
-  "_name_or_path": "openai/whisper-large-v2",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": true,
@@ -54,7 +53,7 @@
   "pad_token_id": 50257,
   "scale_embedding": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.48.0",
+  "transformers_version": "4.52.0",
   "use_cache": true,
   "use_weighted_layer_sum": false,
   "vocab_size": 51865

generation_config.json

@@ -229,5 +229,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.48.0"
+  "transformers_version": "4.52.0"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4da568a59ac91b8552e6f3ea528ad37c777855838670fc3060f614befbe564
+oid sha256:55488db704b8658993bf43b141c3c8890f93f2ce383870fc800ab740d3e06a0e
 size 4992706480

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad925562bc89a272373ae30b8cecda8339794ff8bb9035d5dcdbdfc5e8927e3b
+oid sha256:7ec2cd40e001d1e39772bf00adbbfc3da61f041d1ed55163b4bcefcbcdac11a9
 size 1180663192

preprocessor_config.json

@@ -1,5 +1,6 @@
 {
   "chunk_length": 30,
+  "dither": 0.0,
   "feature_extractor_type": "WhisperFeatureExtractor",
   "feature_size": 80,
   "hop_length": 160,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20adc179b6f798df62ecd414b871514d9da075bfe8a22514841288c4b0d3adc4
+oid sha256:b81d14287daae9f77ad6062bd20a30f1cec7ab6a7e54937d3a802dc14253cfc2
 size 5841