Model save

README.md

@@ -1,42 +1,39 @@
 ---
-language:
-- gl
 license: apache-2.0
 base_model: openai/whisper-tiny
 tags:
-- whisper-event
 - generated_from_trainer
 datasets:
-- mozilla-foundation/common_voice_13_0
+- common_voice_13_0
 metrics:
 - wer
 model-index:
-- name: Whisper Tiny Galician
+- name: openai/whisper-tiny
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: mozilla-foundation/common_voice_13_0 gl
-      type: mozilla-foundation/common_voice_13_0
+      name: common_voice_13_0
+      type: common_voice_13_0
       config: gl
       split: test
       args: gl
     metrics:
     - name: Wer
       type: wer
-      value: 26.35037251655629
+      value: 26.13307119205298
 ---
 
 <!-- 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. -->
 
-# Whisper Tiny Galician
+# openai/whisper-tiny
 
-This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the mozilla-foundation/common_voice_13_0 gl dataset.
+This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the common_voice_13_0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.5832
-- Wer: 26.3504
+- Loss: 0.6003
+- Wer: 26.1331
 
 ## Model description
 
@@ -63,21 +60,22 @@ The following hyperparameters were used during training:
 - 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     |
 |:-------------:|:-----:|:----:|:---------------:|:-------:|
-| 0.0062        | 19.01 | 1000 | 0.5832          | 26.3504 |
-| 0.0012        | 39.01 | 2000 | 0.6527          | 26.7177 |
-| 0.0006        | 59.01 | 3000 | 0.6950          | 27.4352 |
-| 0.0004        | 79.01 | 4000 | 0.7260          | 28.4044 |
-| 0.0003        | 99.01 | 5000 | 0.7315          | 28.1905 |
+| 0.3626        | 20.0  | 1000 | 0.5407          | 30.8464 |
+| 0.1103        | 40.0  | 2000 | 0.5370          | 27.0402 |
+| 0.0473        | 60.0  | 3000 | 0.5769          | 26.7263 |
+| 0.03          | 80.0  | 4000 | 0.5936          | 26.1382 |
+| 0.0244        | 100.0 | 5000 | 0.6003          | 26.1331 |
 
 
 ### Framework versions
 
-- Transformers 4.33.0.dev0
-- Pytorch 2.0.1+cu117
-- Datasets 2.14.4
-- Tokenizers 0.13.3
+- Transformers 4.37.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

generation_config.json

@@ -144,10 +144,11 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "max_initial_timestamp_index": 1,
+  "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,
   "pad_token_id": 50257,
+  "prev_sot_token_id": 50361,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -243,5 +244,5 @@
     "transcribe": 50359,
     "translate": 50358
   },
-  "transformers_version": "4.33.0.dev0"
+  "transformers_version": "4.37.2"
 }