End of training
Browse files
fine-tune-whisper-streaming.ipynb
CHANGED
@@ -413,6 +413,16 @@
|
|
413 |
")"
|
414 |
]
|
415 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
416 |
{
|
417 |
"cell_type": "markdown",
|
418 |
"id": "263a5a58-0239-4a25-b0df-c625fc9c5810",
|
@@ -884,7 +894,9 @@
|
|
884 |
"cell_type": "code",
|
885 |
"execution_count": null,
|
886 |
"id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
|
887 |
-
"metadata": {
|
|
|
|
|
888 |
"outputs": [
|
889 |
{
|
890 |
"name": "stderr",
|
@@ -911,8 +923,8 @@
|
|
911 |
"\n",
|
912 |
" <div>\n",
|
913 |
" \n",
|
914 |
-
" <progress value='
|
915 |
-
" [
|
916 |
" </div>\n",
|
917 |
" <table border=\"1\" class=\"dataframe\">\n",
|
918 |
" <thead>\n",
|
@@ -942,6 +954,12 @@
|
|
942 |
" <td>0.278346</td>\n",
|
943 |
" <td>70.960420</td>\n",
|
944 |
" </tr>\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
945 |
" </tbody>\n",
|
946 |
"</table><p>"
|
947 |
],
|
@@ -1018,6 +1036,28 @@
|
|
1018 |
" Num examples: Unknown\n",
|
1019 |
" Batch size = 8\n",
|
1020 |
"Reading metadata...: 4604it [00:00, 30988.60it/s]\n",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1021 |
"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"
|
1022 |
]
|
1023 |
}
|
@@ -1048,7 +1088,7 @@
|
|
1048 |
},
|
1049 |
{
|
1050 |
"cell_type": "code",
|
1051 |
-
"execution_count":
|
1052 |
"id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
|
1053 |
"metadata": {},
|
1054 |
"outputs": [],
|
|
|
413 |
")"
|
414 |
]
|
415 |
},
|
416 |
+
{
|
417 |
+
"cell_type": "code",
|
418 |
+
"execution_count": null,
|
419 |
+
"id": "ba8b3d77",
|
420 |
+
"metadata": {},
|
421 |
+
"outputs": [],
|
422 |
+
"source": [
|
423 |
+
"vectorized_datasets['train'][0]"
|
424 |
+
]
|
425 |
+
},
|
426 |
{
|
427 |
"cell_type": "markdown",
|
428 |
"id": "263a5a58-0239-4a25-b0df-c625fc9c5810",
|
|
|
894 |
"cell_type": "code",
|
895 |
"execution_count": null,
|
896 |
"id": "ee8b7b8e-1c9a-4d77-9137-1778a629e6de",
|
897 |
+
"metadata": {
|
898 |
+
"scrolled": false
|
899 |
+
},
|
900 |
"outputs": [
|
901 |
{
|
902 |
"name": "stderr",
|
|
|
923 |
"\n",
|
924 |
" <div>\n",
|
925 |
" \n",
|
926 |
+
" <progress value='1001' max='1000' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
|
927 |
+
" [1000/1000 3:35:08, Epoch 7.01/9223372036854775807]\n",
|
928 |
" </div>\n",
|
929 |
" <table border=\"1\" class=\"dataframe\">\n",
|
930 |
" <thead>\n",
|
|
|
954 |
" <td>0.278346</td>\n",
|
955 |
" <td>70.960420</td>\n",
|
956 |
" </tr>\n",
|
957 |
+
" <tr>\n",
|
958 |
+
" <td>800</td>\n",
|
959 |
+
" <td>0.026300</td>\n",
|
960 |
+
" <td>0.298785</td>\n",
|
961 |
+
" <td>74.734005</td>\n",
|
962 |
+
" </tr>\n",
|
963 |
" </tbody>\n",
|
964 |
"</table><p>"
|
965 |
],
|
|
|
1036 |
" Num examples: Unknown\n",
|
1037 |
" Batch size = 8\n",
|
1038 |
"Reading metadata...: 4604it [00:00, 30988.60it/s]\n",
|
1039 |
+
"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",
|
1040 |
+
"Saving model checkpoint to ./checkpoint-800\n",
|
1041 |
+
"Configuration saved in ./checkpoint-800/config.json\n",
|
1042 |
+
"Model weights saved in ./checkpoint-800/pytorch_model.bin\n",
|
1043 |
+
"Feature extractor saved in ./checkpoint-800/preprocessor_config.json\n",
|
1044 |
+
"tokenizer config file saved in ./checkpoint-800/tokenizer_config.json\n",
|
1045 |
+
"Special tokens file saved in ./checkpoint-800/special_tokens_map.json\n",
|
1046 |
+
"added tokens file saved in ./checkpoint-800/added_tokens.json\n",
|
1047 |
+
"Feature extractor saved in ./preprocessor_config.json\n",
|
1048 |
+
"tokenizer config file saved in ./tokenizer_config.json\n",
|
1049 |
+
"Special tokens file saved in ./special_tokens_map.json\n",
|
1050 |
+
"added tokens file saved in ./added_tokens.json\n",
|
1051 |
+
"Reading metadata...: 6505it [00:00, 36357.17it/s]\n",
|
1052 |
+
"Reading metadata...: 4485it [00:00, 30574.75it/s]\n",
|
1053 |
+
"Got disconnected from remote data host. Retrying in 5sec [1/20]\n",
|
1054 |
+
"Got disconnected from remote data host. Retrying in 5sec [2/20]\n",
|
1055 |
+
"Reading metadata...: 6505it [00:00, 31147.16it/s]\n",
|
1056 |
+
"Reading metadata...: 4485it [00:00, 22808.34it/s]\n",
|
1057 |
+
"***** Running Evaluation *****\n",
|
1058 |
+
" Num examples: Unknown\n",
|
1059 |
+
" Batch size = 8\n",
|
1060 |
+
"Reading metadata...: 4604it [00:00, 28132.71it/s]\n",
|
1061 |
"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"
|
1062 |
]
|
1063 |
}
|
|
|
1088 |
},
|
1089 |
{
|
1090 |
"cell_type": "code",
|
1091 |
+
"execution_count": null,
|
1092 |
"id": "6dd0e310-9b07-4133-ac14-2ed2d7524e22",
|
1093 |
"metadata": {},
|
1094 |
"outputs": [],
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 967102601
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9e06d3e42c138244efef713a71edd16e7d80d9f5c735a8f6d28405049e4324d
|
3 |
size 967102601
|
runs/Dec12_04-37-47_150-136-44-233/events.out.tfevents.1670819878.150-136-44-233.69039.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20668955bf6ac4ed0191c828632dc5874d4c9cb7dfe05a85c9fc6570e9639479
|
3 |
+
size 11822
|