End of training

README.md

@@ -1,25 +1,27 @@
 ---
 library_name: transformers
+language:
+- nan
 license: apache-2.0
 base_model: openai/whisper-medium
 tags:
 - generated_from_trainer
 datasets:
-- common_voice_16_1
+- mozilla-foundation/common_voice_16_1
 metrics:
 - wer
 model-index:
-- name: whisper_new_ver3
+- name: Hokkien-to-Tai Lo Whisper ver 3
   results:
   - task:
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
     dataset:
-      name: common_voice_16_1
-      type: common_voice_16_1
+      name: Common Voice 16.0
+      type: mozilla-foundation/common_voice_16_1
       config: nan-tw
       split: test
-      args: nan-tw
+      args: 'config: hi, split: test'
     metrics:
     - name: Wer
       type: wer
@@ -29,9 +31,9 @@ model-index:
 <!-- 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_new_ver3
+# Hokkien-to-Tai Lo Whisper ver 3
 
-This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the common_voice_16_1 dataset.
+This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 16.0 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.5026
 - Wer: 82.8578

preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 80,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}