update model card README.md

README.md

@@ -0,0 +1,81 @@
+---
+language:
+- hy
+license: apache-2.0
+tags:
+- whisper-event
+- generated_from_trainer
+datasets:
+- mozilla-foundation/common_voice_11_0
+metrics:
+- wer
+model-index:
+- name: Whisper
+  results:
+  - task:
+      name: Automatic Speech Recognition
+      type: automatic-speech-recognition
+    dataset:
+      name: common_voice_11_0
+      type: mozilla-foundation/common_voice_11_0
+      config: hy-AM
+      split: test
+      args: hy-AM
+    metrics:
+    - name: Wer
+      type: wer
+      value: 39.73684210526316
+---
+
+<!-- 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
+
+This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4380
+- Wer: 39.7368
+
+## 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-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- training_steps: 1500
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Wer     |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|
+| 0.0001        | 34.0  | 1500 | 0.4380          | 39.7368 |
+
+
+### Framework versions
+
+- Transformers 4.26.0.dev0
+- Pytorch 1.13.1+cu117
+- Datasets 2.7.1.dev0
+- Tokenizers 0.13.2

fine-tune-whisper-streaming.ipynb

@@ -908,7 +908,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 23,
    "id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
    "metadata": {},
    "outputs": [
@@ -937,8 +937,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='1501' max='1500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1500/1500 1:57:29, Epoch 34.00/9223372036854775807]\n",
+       "      <progress value='1500' max='1500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [1500/1500 2:21:47, Epoch 34/9223372036854775807]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -946,9 +946,16 @@
        "      <th>Step</th>\n",
        "      <th>Training Loss</th>\n",
        "      <th>Validation Loss</th>\n",
+       "      <th>Wer</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>1500</td>\n",
+       "      <td>0.000100</td>\n",
+       "      <td>0.437977</td>\n",
+       "      <td>39.736842</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
        "</table><p>"
       ],
@@ -1787,8 +1794,35 @@
       "  \"transformers_version\": \"4.26.0.dev0\",\n",
       "  \"use_cache\": false\n",
       "}\n",
-      "\n"
+      "\n",
+      "Saving model checkpoint to ./checkpoint-1500\n",
+      "Configuration saved in ./checkpoint-1500/config.json\n",
+      "Model weights saved in ./checkpoint-1500/pytorch_model.bin\n",
+      "Feature extractor saved in ./checkpoint-1500/preprocessor_config.json\n",
+      "tokenizer config file saved in ./checkpoint-1500/tokenizer_config.json\n",
+      "Special tokens file saved in ./checkpoint-1500/special_tokens_map.json\n",
+      "added tokens file saved in ./checkpoint-1500/added_tokens.json\n",
+      "Feature extractor saved in ./preprocessor_config.json\n",
+      "tokenizer config file saved in ./tokenizer_config.json\n",
+      "Special tokens file saved in ./special_tokens_map.json\n",
+      "added tokens file saved in ./added_tokens.json\n",
+      "\n",
+      "\n",
+      "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
+      "\n",
+      "\n",
+      "Loading best model from ./checkpoint-1500 (score: 39.73684210526316).\n"
      ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "TrainOutput(global_step=1500, training_loss=0.03859770913313453, metrics={'train_runtime': 8541.9827, 'train_samples_per_second': 2.81, 'train_steps_per_second': 0.176, 'total_flos': 5.15336070168576e+19, 'train_loss': 0.03859770913313453, 'epoch': 34.0})"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
@@ -1817,7 +1851,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 24,
    "id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
    "metadata": {},
    "outputs": [],
@@ -1846,7 +1880,25 @@
    "execution_count": null,
    "id": "95737cda-c5dd-4887-a4d0-dfcb0d61d977",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Saving model checkpoint to ./\n",
+      "Configuration saved in ./config.json\n",
+      "Model weights saved in ./pytorch_model.bin\n",
+      "Feature extractor saved in ./preprocessor_config.json\n",
+      "tokenizer config file saved in ./tokenizer_config.json\n",
+      "Special tokens file saved in ./special_tokens_map.json\n",
+      "added tokens file saved in ./added_tokens.json\n",
+      "Several commits (2) will be pushed upstream.\n",
+      "The progress bars may be unreliable.\n",
+      "Upload file pytorch_model.bin:   0%|                                                                                                            | 1.00/5.75G [00:00<?, ?B/s]\n",
+      "Upload file runs/Dec19_10-11-44_132-145-194-8/events.out.tfevents.1671444716.132-145-194-8.3465423.0:   0%|                                     | 1.00/14.0k [00:00<?, ?B/s]\u001b[A"
+     ]
+    }
+   ],
    "source": [
     "trainer.push_to_hub(**kwargs)"
    ]