Training in progress, step 1000

.ipynb_checkpoints/eval-checkpoint.py

@@ -0,0 +1,132 @@
+#!/usr/bin/env python3
+from datasets import load_dataset, load_metric, Audio, Dataset
+from transformers import pipeline, AutoFeatureExtractor
+import re
+import argparse
+import unicodedata
+from typing import Dict
+
+
+def log_results(result: Dataset, args: Dict[str, str]):
+    """ DO NOT CHANGE. This function computes and logs the result metrics. """
+
+    log_outputs = args.log_outputs
+    dataset_id = "_".join(args.dataset.split("/") + [args.config, args.split])
+
+    # load metric
+    wer = load_metric("wer")
+    cer = load_metric("cer")
+
+    # compute metrics
+    wer_result = wer.compute(references=result["target"], predictions=result["prediction"])
+    cer_result = cer.compute(references=result["target"], predictions=result["prediction"])
+
+    # print & log results
+    result_str = (
+        f"WER: {wer_result}\n"
+        f"CER: {cer_result}"
+    )
+    print(result_str)
+
+    with open(f"{dataset_id}_eval_results.txt", "w") as f:
+        f.write(result_str)
+
+    # log all results in text file. Possibly interesting for analysis
+    if log_outputs is not None:
+        pred_file = f"log_{dataset_id}_predictions.txt"
+        target_file = f"log_{dataset_id}_targets.txt"
+
+        with open(pred_file, "w") as p, open(target_file, "w") as t:
+
+            # mapping function to write output
+            def write_to_file(batch, i):
+                p.write(f"{i}" + "\n")
+                p.write(batch["prediction"] + "\n")
+                t.write(f"{i}" + "\n")
+                t.write(batch["target"] + "\n")
+
+            result.map(write_to_file, with_indices=True)
+
+
+def normalize_text(text: str) -> str:
+    """ DO ADAPT FOR YOUR USE CASE. this function normalizes the target text. """
+
+    from pykakasi import kakasi
+
+    kakasi = kakasi()
+    kakasi.setMode('J', 'H') #Convert from kanji to hiragana
+    conv = kakasi.getConverter()
+    chars_to_ignore_regex = '[\,\?\!\-\;\:\"\“\%\‘\”\�\—\’\…\–\（\，\[\]\)\(\！]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
+
+    text = text.lower()
+    # normalize non-standard (stylized) unicode characters
+    text = unicodedata.normalize('NFKC', text)
+    # remove punctuation
+    text = conv.do(re.sub(chars_to_ignore_regex, "", text))
+    
+    # Let's also make sure we split on all kinds of newlines, spaces, etc...
+    text = " ".join(text.split())
+
+    return text
+
+
+def main(args):
+    # load dataset
+    dataset = load_dataset(args.dataset, args.config, split=args.split, use_auth_token=True)
+
+    # for testing: only process the first two examples as a test
+    # dataset = dataset.select(range(10))
+
+    # load processor
+    feature_extractor = AutoFeatureExtractor.from_pretrained(args.model_id)
+    sampling_rate = feature_extractor.sampling_rate
+
+    # resample audio
+    dataset = dataset.cast_column("audio", Audio(sampling_rate=sampling_rate))
+
+    # load eval pipeline
+    asr = pipeline("automatic-speech-recognition", model=args.model_id)
+
+    # map function to decode audio
+    def map_to_pred(batch):
+        prediction = asr(batch["audio"]["array"], chunk_length_s=args.chunk_length_s, stride_length_s=args.stride_length_s)
+
+        batch["prediction"] = prediction["text"]
+        batch["target"] = normalize_text(batch["sentence"])
+        return batch
+
+    # run inference on all examples
+    result = dataset.map(map_to_pred, remove_columns=dataset.column_names)
+
+    # compute and log_results
+    # do not change function below
+    log_results(result, args)
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+
+    parser.add_argument(
+        "--model_id", type=str, required=True, help="Model identifier. Should be loadable with 🤗 Transformers"
+    )
+    parser.add_argument(
+        "--dataset", type=str, required=True, help="Dataset name to evaluate the `model_id`. Should be loadable with 🤗 Datasets"
+    )
+    parser.add_argument(
+        "--config", type=str, required=True, help="Config of the dataset. *E.g.* `'en'`  for Common Voice"
+    )
+    parser.add_argument(
+        "--split", type=str, required=True, help="Split of the dataset. *E.g.* `'test'`"
+    )
+    parser.add_argument(
+        "--chunk_length_s", type=float, default=None, help="Chunk length in seconds. Defaults to None. For long audio files a good value would be 5.0 seconds."
+    )
+    parser.add_argument(
+        "--stride_length_s", type=float, default=None, help="Stride of the audio chunks. Defaults to None. For long audio files a good value would be 1.0 seconds."
+    )
+    parser.add_argument(
+        "--log_outputs", action='store_true', help="If defined, write outputs to log file for analysis."
+    )
+    args = parser.parse_args()
+
+    main(args)

.ipynb_checkpoints/eval_results-checkpoint.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.9563776254653931,
+    "eval_runtime": 234.4791,
+    "eval_samples": 4483,
+    "eval_samples_per_second": 19.119,
+    "eval_steps_per_second": 2.393,
+    "eval_wer": 2.4134786476868326
+}

.ipynb_checkpoints/run_training-checkpoint.sh

@@ -4,7 +4,7 @@ python run_speech_recognition_ctc_bnb.py \
 	--dataset_config_name="ja" \
 	--output_dir="./" \
     --overwrite_output_dir \
-	--num_train_epochs="10" \
+	--num_train_epochs="50" \
 	--per_device_train_batch_size="48" \
 	--per_device_eval_batch_size="8" \
 	--learning_rate="7.5e-5" \

.ipynb_checkpoints/speech_training_notebook-checkpoint.ipynb

@@ -327,6 +327,98 @@
     "common_voice_test = common_voice_test.map(remove_special_characters)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'client_id': '02a8841a00d762472a4797b56ee01643e8d9ece5a225f2e91c007ab1f94c49c99e50d19986ff3fefb18190257323f34238828114aa607f84fbe9764ecf5aaeaa',\n",
+       " 'path': 'cv-corpus-8.0-2022-01-19/ja/clips/common_voice_ja_25467658.mp3',\n",
+       " 'audio': {'path': 'cv-corpus-8.0-2022-01-19/ja/clips/common_voice_ja_25467658.mp3',\n",
+       "  'array': array([0.        , 0.        , 0.        , ..., 0.00026336, 0.00038834,\n",
+       "         0.00026771], dtype=float32),\n",
+       "  'sampling_rate': 48000},\n",
+       " 'sentence': 'ちょっとがっこうでトラブルがありまして。',\n",
+       " 'up_votes': 2,\n",
+       " 'down_votes': 0,\n",
+       " 'age': 'fourties',\n",
+       " 'gender': 'female',\n",
+       " 'accent': '',\n",
+       " 'locale': 'ja',\n",
+       " 'segment': ''}"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "common_voice_train[1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: datasets in /opt/conda/lib/python3.8/site-packages (1.18.2.dev0)\n",
+      "Collecting datasets\n",
+      "  Downloading datasets-1.18.3-py3-none-any.whl (311 kB)\n",
+      "     |████████████████████████████████| 311 kB 11.0 MB/s            \n",
+      "\u001b[?25hRequirement already satisfied: aiohttp in /opt/conda/lib/python3.8/site-packages (from datasets) (3.8.1)\n",
+      "Requirement already satisfied: huggingface-hub<1.0.0,>=0.1.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (0.4.0)\n",
+      "Requirement already satisfied: dill in /opt/conda/lib/python3.8/site-packages (from datasets) (0.3.4)\n",
+      "Requirement already satisfied: xxhash in /opt/conda/lib/python3.8/site-packages (from datasets) (2.0.2)\n",
+      "Requirement already satisfied: multiprocess in /opt/conda/lib/python3.8/site-packages (from datasets) (0.70.12.2)\n",
+      "Requirement already satisfied: pandas in /opt/conda/lib/python3.8/site-packages (from datasets) (1.4.0)\n",
+      "Requirement already satisfied: pyarrow!=4.0.0,>=3.0.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (6.0.1)\n",
+      "Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (2.24.0)\n",
+      "Requirement already satisfied: fsspec[http]>=2021.05.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (2022.1.0)\n",
+      "Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.8/site-packages (from datasets) (1.19.2)\n",
+      "Requirement already satisfied: tqdm>=4.62.1 in /opt/conda/lib/python3.8/site-packages (from datasets) (4.62.3)\n",
+      "Requirement already satisfied: packaging in /opt/conda/lib/python3.8/site-packages (from datasets) (21.3)\n",
+      "Requirement already satisfied: filelock in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (3.0.12)\n",
+      "Requirement already satisfied: pyyaml in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (5.4.1)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (4.0.1)\n",
+      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.8/site-packages (from packaging->datasets) (3.0.7)\n",
+      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (1.25.11)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (2020.12.5)\n",
+      "Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (3.0.4)\n",
+      "Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (2.10)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (6.0.2)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.3.0)\n",
+      "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (2.0.10)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.7.2)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (21.4.0)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.2.0)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (4.0.2)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.8/site-packages (from pandas->datasets) (2021.1)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.1 in /opt/conda/lib/python3.8/site-packages (from pandas->datasets) (2.8.2)\n",
+      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.8/site-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.15.0)\n",
+      "Installing collected packages: datasets\n",
+      "  Attempting uninstall: datasets\n",
+      "    Found existing installation: datasets 1.18.2.dev0\n",
+      "    Uninstalling datasets-1.18.2.dev0:\n",
+      "\u001b[31mERROR: Could not install packages due to an OSError: [Errno 13] Permission denied: 'entry_points.txt'\n",
+      "Consider using the `--user` option or check the permissions.\n",
+      "\u001b[0m\n",
+      "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.2 is available.\n",
+      "You should consider upgrading via the '/opt/conda/bin/python -m pip install --upgrade pip' command.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install --upgrade datasets"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9c7d3bf0321f7ec331f1d799ed4e041f8144ab66c8ed7f7fe296a6de4f12ad3
+oid sha256:416e43f69cc98a936f068cbc6b786eded59831d04ed15bbf501c4040a5a2b996
 size 1262956849

run_training.sh

@@ -4,7 +4,7 @@ python run_speech_recognition_ctc_bnb.py \
 	--dataset_config_name="ja" \
 	--output_dir="./" \
     --overwrite_output_dir \
-	--num_train_epochs="10" \
+	--num_train_epochs="50" \
 	--per_device_train_batch_size="48" \
 	--per_device_eval_batch_size="8" \
 	--learning_rate="7.5e-5" \

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

speech_training_notebook.ipynb

@@ -360,6 +360,65 @@
     "common_voice_train[1]"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: datasets in /opt/conda/lib/python3.8/site-packages (1.18.2.dev0)\n",
+      "Collecting datasets\n",
+      "  Downloading datasets-1.18.3-py3-none-any.whl (311 kB)\n",
+      "     |████████████████████████████████| 311 kB 11.0 MB/s            \n",
+      "\u001b[?25hRequirement already satisfied: aiohttp in /opt/conda/lib/python3.8/site-packages (from datasets) (3.8.1)\n",
+      "Requirement already satisfied: huggingface-hub<1.0.0,>=0.1.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (0.4.0)\n",
+      "Requirement already satisfied: dill in /opt/conda/lib/python3.8/site-packages (from datasets) (0.3.4)\n",
+      "Requirement already satisfied: xxhash in /opt/conda/lib/python3.8/site-packages (from datasets) (2.0.2)\n",
+      "Requirement already satisfied: multiprocess in /opt/conda/lib/python3.8/site-packages (from datasets) (0.70.12.2)\n",
+      "Requirement already satisfied: pandas in /opt/conda/lib/python3.8/site-packages (from datasets) (1.4.0)\n",
+      "Requirement already satisfied: pyarrow!=4.0.0,>=3.0.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (6.0.1)\n",
+      "Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (2.24.0)\n",
+      "Requirement already satisfied: fsspec[http]>=2021.05.0 in /opt/conda/lib/python3.8/site-packages (from datasets) (2022.1.0)\n",
+      "Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.8/site-packages (from datasets) (1.19.2)\n",
+      "Requirement already satisfied: tqdm>=4.62.1 in /opt/conda/lib/python3.8/site-packages (from datasets) (4.62.3)\n",
+      "Requirement already satisfied: packaging in /opt/conda/lib/python3.8/site-packages (from datasets) (21.3)\n",
+      "Requirement already satisfied: filelock in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (3.0.12)\n",
+      "Requirement already satisfied: pyyaml in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (5.4.1)\n",
+      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.8/site-packages (from huggingface-hub<1.0.0,>=0.1.0->datasets) (4.0.1)\n",
+      "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.8/site-packages (from packaging->datasets) (3.0.7)\n",
+      "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (1.25.11)\n",
+      "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (2020.12.5)\n",
+      "Requirement already satisfied: chardet<4,>=3.0.2 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (3.0.4)\n",
+      "Requirement already satisfied: idna<3,>=2.5 in /opt/conda/lib/python3.8/site-packages (from requests>=2.19.0->datasets) (2.10)\n",
+      "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (6.0.2)\n",
+      "Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.3.0)\n",
+      "Requirement already satisfied: charset-normalizer<3.0,>=2.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (2.0.10)\n",
+      "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.7.2)\n",
+      "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (21.4.0)\n",
+      "Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (1.2.0)\n",
+      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /opt/conda/lib/python3.8/site-packages (from aiohttp->datasets) (4.0.2)\n",
+      "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.8/site-packages (from pandas->datasets) (2021.1)\n",
+      "Requirement already satisfied: python-dateutil>=2.8.1 in /opt/conda/lib/python3.8/site-packages (from pandas->datasets) (2.8.2)\n",
+      "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.8/site-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.15.0)\n",
+      "Installing collected packages: datasets\n",
+      "  Attempting uninstall: datasets\n",
+      "    Found existing installation: datasets 1.18.2.dev0\n",
+      "    Uninstalling datasets-1.18.2.dev0:\n",
+      "\u001b[31mERROR: Could not install packages due to an OSError: [Errno 13] Permission denied: 'entry_points.txt'\n",
+      "Consider using the `--user` option or check the permissions.\n",
+      "\u001b[0m\n",
+      "\u001b[33mWARNING: You are using pip version 21.3.1; however, version 22.0.2 is available.\n",
+      "You should consider upgrading via the '/opt/conda/bin/python -m pip install --upgrade pip' command.\u001b[0m\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install --upgrade datasets"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 6,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e27818f3fc71ffdfcc80419d1967fd61208e9dc6b1b3d61fd6629f0946734b
+oid sha256:093731fe91be156fc7e4a872c63f46f6ccef7059d892048324989ebf1c39c91e
 size 2991