Training in progress, step 2000

fine-tune-whisper-streaming.ipynb

@@ -1076,8 +1076,8 @@
        "\n",
        "    <div>\n",
        "      \n",
-       "      <progress value='1001' max='2000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-       "      [1001/2000 1:49:55 < 1:49:55, 0.15 it/s, Epoch 8.04/9223372036854775807]\n",
+       "      <progress value='2001' max='2000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [2000/2000 4:01:33, Epoch 17.01/9223372036854775807]\n",
        "    </div>\n",
        "    <table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
@@ -1085,9 +1085,16 @@
        "      <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>1000</td>\n",
+       "      <td>0.009000</td>\n",
+       "      <td>0.444009</td>\n",
+       "      <td>34.279589</td>\n",
+       "    </tr>\n",
        "  </tbody>\n",
        "</table><p>"
       ],
@@ -1122,6 +1129,40 @@
       "  Num examples: Unknown\n",
       "  Batch size = 8\n",
       "Reading metadata...: 3749it [00:00, 17477.47it/s]\n",
+      "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n",
+      "Saving model checkpoint to ./checkpoint-1000\n",
+      "Configuration saved in ./checkpoint-1000/config.json\n",
+      "Model weights saved in ./checkpoint-1000/pytorch_model.bin\n",
+      "Feature extractor saved in ./checkpoint-1000/preprocessor_config.json\n",
+      "tokenizer config file saved in ./checkpoint-1000/tokenizer_config.json\n",
+      "Special tokens file saved in ./checkpoint-1000/special_tokens_map.json\n",
+      "added tokens file saved in ./checkpoint-1000/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",
+      "Reading metadata...: 5194it [00:00, 85044.01it/s]\n",
+      "Reading metadata...: 3690it [00:00, 74377.46it/s]\n",
+      "Reading metadata...: 5194it [00:00, 80124.52it/s]\n",
+      "Reading metadata...: 3690it [00:00, 67032.13it/s]\n",
+      "Reading metadata...: 5194it [00:00, 71957.77it/s]\n",
+      "Reading metadata...: 3690it [00:00, 57010.29it/s]\n",
+      "Reading metadata...: 5194it [00:00, 15179.43it/s]\n",
+      "Reading metadata...: 3690it [00:00, 11107.82it/s]\n",
+      "Reading metadata...: 5194it [00:00, 85555.35it/s]\n",
+      "Reading metadata...: 3690it [00:00, 68384.18it/s]\n",
+      "Reading metadata...: 5194it [00:00, 18672.38it/s]\n",
+      "Reading metadata...: 3690it [00:00, 28625.03it/s]\n",
+      "Reading metadata...: 5194it [00:00, 84027.47it/s]\n",
+      "Reading metadata...: 3690it [00:00, 62199.27it/s]\n",
+      "Reading metadata...: 5194it [00:00, 58151.75it/s]\n",
+      "Reading metadata...: 3690it [00:00, 59150.79it/s]\n",
+      "Reading metadata...: 5194it [00:00, 83226.87it/s]\n",
+      "Reading metadata...: 3690it [00:00, 70468.75it/s]\n",
+      "***** Running Evaluation *****\n",
+      "  Num examples: Unknown\n",
+      "  Batch size = 8\n",
+      "Reading metadata...: 3749it [00:00, 23184.29it/s]\n",
       "The following columns in the evaluation set don't have a corresponding argument in `WhisperForConditionalGeneration.forward` and have been ignored: input_length. If input_length are not expected by `WhisperForConditionalGeneration.forward`,  you can safely ignore this message.\n"
      ]
     }
@@ -1160,8 +1201,8 @@
     "kwargs = {\n",
     "    \"dataset_tags\": \"mozilla-foundation/common_voice_11_0\",\n",
     "    \"dataset\": \"Common Voice 11.0\",  # a 'pretty' name for the training dataset\n",
-    "    \"language\": \"es\",\n",
-    "    \"model_name\": \"Whisper Small Es - Sanchit Gandhi\",  # a 'pretty' name for your model\n",
+    "    \"language\": \"lt\",\n",
+    "    \"model_name\": \"Whisper Small Lt and Sr\",  # a 'pretty' name for your model\n",
     "    \"finetuned_from\": \"openai/whisper-small\",\n",
     "    \"tasks\": \"automatic-speech-recognition\",\n",
     "    \"tags\": \"whisper-event\",\n",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcacfb0660cd4988d52dadcf3cbb552b750719fc75b2528b7a643958ad036298
+oid sha256:5a11f74090959c07ae26487bc3ce05849151ba32d0f718c8ab6924c218bbc666
 size 967102601

runs/Dec15_09-48-30_129-213-18-196/events.out.tfevents.1671097754.129-213-18-196.69807.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4609057e868246bd5a3d73b76ce96fe8a932bfc60044e62c7f13af775af4abf9
-size 10870
+oid sha256:0c18ec6a9ca2b818981f832541fefb0d38fab7f8805614f1308ce1609f3f6941
+size 17468