End of training

README.md

@@ -1,40 +1,43 @@
 ---
 library_name: transformers
+language:
+- zh
 license: apache-2.0
 base_model: openai/whisper-small
 tags:
 - generated_from_trainer
 datasets:
-- common_voice_11_0
+- mozilla-foundation/common_voice_11_0
 metrics:
 - wer
 model-index:
-- name: whisper-small-chinese-tw-minnan
+- name: Whisper Small chinese Test
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_11_0
-      type: common_voice_11_0
+      name: Common Voice 11.0
+      type: mozilla-foundation/common_voice_11_0
       config: nan-tw
       split: test
-      args: nan-tw
+      args: 'config: zh-tw, split: test'
     metrics:
     - name: Wer
       type: wer
-      value: 94.0629839958699
+      value: 83.97565922920892
 ---
 
 <!-- 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-small-chinese-tw-minnan
+# Whisper Small chinese Test
 
-This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the common_voice_11_0 dataset.
+This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9213
-- Wer: 94.0630
+- Loss: 1.2154
+- Wer: 83.9757
+- Cer: 56.8934
 
 ## Model description
 
@@ -65,13 +68,13 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch   | Step | Validation Loss | Wer     |
-|:-------------:|:-------:|:----:|:---------------:|:-------:|
-| 0.1069        | 3.6364  | 1000 | 0.7541          | 99.3289 |
-| 0.0117        | 7.2727  | 2000 | 0.8330          | 93.9597 |
-| 0.0015        | 10.9091 | 3000 | 0.8627          | 94.7858 |
-| 0.0004        | 14.5455 | 4000 | 0.9036          | 93.3918 |
-| 0.0002        | 18.1818 | 5000 | 0.9213          | 94.0630 |
+| Training Loss | Epoch   | Step | Validation Loss | Wer     | Cer     |
+|:-------------:|:-------:|:----:|:---------------:|:-------:|:-------:|
+| 0.0841        | 3.6364  | 1000 | 1.1602          | 87.9310 | 69.9880 |
+| 0.0025        | 7.2727  | 2000 | 1.1670          | 82.9615 | 57.7664 |
+| 0.0021        | 10.9091 | 3000 | 1.1896          | 84.4828 | 58.3082 |
+| 0.0001        | 14.5455 | 4000 | 1.2104          | 83.5700 | 56.8934 |
+| 0.0001        | 18.1818 | 5000 | 1.2154          | 83.9757 | 56.8934 |
 
 
 ### Framework versions

generation_config.json

@@ -150,7 +150,7 @@
     "<|yo|>": 50325,
     "<|zh|>": 50260
   },
-  "language": "chinese",
+  "language": null,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
   "no_timestamps_token_id": 50363,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184dc94298c005a0b4fc0c213d964c7a3d26dc9dfb950a8d029b4704b4c7c300
+oid sha256:a5064c2aa2567684007dbd37a2dd48cd39240eeddda9c6a6156c274f0811d54d
 size 966995080