modify training files

.ipynb_checkpoints/README-checkpoint.md

@@ -1,105 +0,0 @@
----
-language:
-- fr
-license: apache-2.0
-tags:
-- automatic-speech-recognition
-- mozilla-foundation/common_voice_8_0
-- generated_from_trainer
-- robust-speech-event
-model-index:
-- name: XLS-R-1B - French
-  results:
-  - task: 
-      name: Automatic Speech Recognition 
-      type: automatic-speech-recognition
-    dataset:
-      name: Common Voice 8
-      type: mozilla-foundation/common_voice_8_0
-      args: fr
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 18.33
-       - name: Test CER
-         type: cer
-         value: 5.60
-  - task:
-      name: Automatic Speech Recognition
-      type: automatic-speech-recognition
-    dataset:
-      name: Robust Speech Event - Dev Data
-      type: speech-recognition-community-v2/dev_data
-      args: fr
-    metrics:
-       - name: Test WER
-         type: wer
-         value: 60.25
-       - name: Test CER
-         type: cer
-         value: 15.68
----
-
-## Model description
-
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FR dataset.
-
-## Training procedure
-
-### Training hyperparameters
-
-The following hyperparameters were used during training:
-- learning_rate: 7.5e-05
-- train_batch_size: 16
-- eval_batch_size: 16
-- seed: 42
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 128
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- lr_scheduler_warmup_steps: 2000
-- num_epochs: 4.0
-- mixed_precision_training: Native AMP
-
-### Training results
-
-| Training Loss | Epoch | Step  | Validation Loss | Wer    |
-|:-------------:|:-----:|:-----:|:---------------:|:------:|
-| 0.9827        | 0.29  | 1000  | inf             | 0.2937 |
-| 1.0203        | 0.57  | 2000  | inf             | 0.2711 |
-| 1.0048        | 0.86  | 3000  | inf             | 0.2620 |
-| 0.9858        | 1.15  | 4000  | inf             | 0.2522 |
-| 0.9709        | 1.43  | 5000  | inf             | 0.2365 |
-| 0.9347        | 1.72  | 6000  | inf             | 0.2332 |
-| 0.9256        | 2.01  | 7000  | inf             | 0.2261 |
-| 0.8936        | 2.29  | 8000  | inf             | 0.2203 |
-| 0.877         | 2.58  | 9000  | inf             | 0.2096 |
-| 0.8393        | 2.87  | 10000 | inf             | 0.2017 |
-| 0.8156        | 3.15  | 11000 | inf             | 0.1936 |
-| 0.8015        | 3.44  | 12000 | inf             | 0.1880 |
-| 0.774         | 3.73  | 13000 | inf             | 0.1834 |
-
-It achieves the best result on the validation set on STEP 13000:
-- Wer: 0.1834
-
-Some problem occurs when calculating the validation loss.
-
-### Framework versions
-
-- Transformers 4.17.0.dev0
-- Pytorch 1.10.2+cu102
-- Datasets 1.18.3.dev0
-- Tokenizers 0.11.0
-
-### Evaluation Commands
-1. To evaluate on `mozilla-foundation/common_voice_8` with split `test`
-
-```bash
-python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset mozilla-foundation/common_voice_8_0 --config fr --split test
-```
-
-2. To evaluate on `speech-recognition-community-v2/dev_data`
-
-```bash
-python eval.py --model_id Plim/xls-r-1b-cv_8-fr --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0
-```

.ipynb_checkpoints/create_lm-checkpoint.ipynb

@@ -1,309 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "id": "7b5f7142",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "import transformers\n",
-    "from datasets import load_dataset\n",
-    "import re"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "id": "4ad6422f",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "username = \"Plim\"  # change to your username\n",
-    "target_lang = \"fr\""
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "id": "37b2c1d6",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f230feb459c441a9a11e53b867e8914a",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/2.60k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a4a8fa35d48f4a6db8072baed6b2389b",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/29.6k [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "Using custom data configuration en-fr-lang1=en,lang2=fr\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Downloading and preparing dataset europarl_bilingual/en-fr (download: 278.07 MiB, generated: 643.66 MiB, post-processed: Unknown size, total: 921.72 MiB) to /workspace/.cache/huggingface/datasets/europarl_bilingual/en-fr-lang1=en,lang2=fr/8.0.0/2ab0200e7729616bfd4a4df6bfb29b31746ceb5a59f8c75c02ca35e1ebead950...\n"
-     ]
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aa00b5d6dc154449861dddcf9f0d2fc8",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/142M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "563096fc78454333b5ae23e87a7e3469",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/140M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eba05e5151b34505b9a43e383cb6cfe0",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Downloading:   0%|          | 0.00/9.30M [00:00<?, ?B/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "0 examples [00:00, ? examples/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Dataset europarl_bilingual downloaded and prepared to /workspace/.cache/huggingface/datasets/europarl_bilingual/en-fr-lang1=en,lang2=fr/8.0.0/2ab0200e7729616bfd4a4df6bfb29b31746ceb5a59f8c75c02ca35e1ebead950. Subsequent calls will reuse this data.\n"
-     ]
-    }
-   ],
-   "source": [
-    "dataset = load_dataset(\"europarl_bilingual\", lang1=\"en\", lang2=target_lang, split=\"train\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "id": "81259294",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def extract_text(batch):\n",
-    "    target_lang = \"fr\"\n",
-    "    chars_to_ignore_regex = '[^a-zàâäçéèêëîïôöùûüÿ\\'’ ]'\n",
-    "    text = batch[\"translation\"][target_lang]\n",
-    "    batch[\"text\"] = re.sub(chars_to_ignore_regex, \"\", text.lower()).replace('’', \"'\")\n",
-    "    return batch"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "id": "2dec7b80",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "00d998de52544f6c8750c53bc0c85d66",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "0ex [00:00, ?ex/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "dataset = dataset.map(extract_text, remove_columns=dataset.column_names)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "id": "c6feaf74",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "461a219cdb6d42b2b890ec028c336e7f",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "Pushing dataset shards to the dataset hub:   0%|          | 0/1 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "dataset.push_to_hub(f\"{target_lang}_corpora_parliament_processed\", split=\"train\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "id": "b0e6ae25",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open(\"text.txt\", \"w\") as file:\n",
-    "    file.write(\" \".join(dataset[\"text\"]))"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 17,
-   "id": "f95596a5",
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "with open(\"5gram.arpa\", \"r\") as read_file, open(\"5gram_correct.arpa\", \"w\") as write_file:\n",
-    "    has_added_eos = False\n",
-    "    for line in read_file:\n",
-    "        if not has_added_eos and \"ngram 1=\" in line:\n",
-    "            count=line.strip().split(\"=\")[-1]\n",
-    "            write_file.write(line.replace(f\"{count}\", f\"{int(count)+1}\"))\n",
-    "        elif not has_added_eos and \"<s>\" in line:\n",
-    "            write_file.write(line)\n",
-    "            write_file.write(line.replace(\"<s>\", \"</s>\"))\n",
-    "            has_added_eos = True\n",
-    "        else:\n",
-    "            write_file.write(line)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "id": "f6489f25",
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "file ./config.json not found\n"
-     ]
-    },
-    {
-     "ename": "OSError",
-     "evalue": "Can't load config for './'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './' is the correct path to a directory containing a config.json file",
-     "output_type": "error",
-     "traceback": [
-      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
-      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:585\u001b[0m, in \u001b[0;36mPretrainedConfig._get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    583\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    584\u001b[0m     \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 585\u001b[0m     resolved_config_file \u001b[38;5;241m=\u001b[39m \u001b[43mcached_path\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    586\u001b[0m \u001b[43m        \u001b[49m\u001b[43mconfig_file\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    587\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    588\u001b[0m \u001b[43m        \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    589\u001b[0m \u001b[43m        \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    590\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    591\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    592\u001b[0m \u001b[43m        \u001b[49m\u001b[43muse_auth_token\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_auth_token\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    593\u001b[0m \u001b[43m        \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    594\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    596\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RepositoryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m err:\n",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/file_utils.py:1861\u001b[0m, in \u001b[0;36mcached_path\u001b[0;34m(url_or_filename, cache_dir, force_download, proxies, resume_download, user_agent, extract_compressed_file, force_extract, use_auth_token, local_files_only)\u001b[0m\n\u001b[1;32m   1859\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m urlparse(url_or_filename)\u001b[38;5;241m.\u001b[39mscheme \u001b[38;5;241m==\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m:\n\u001b[1;32m   1860\u001b[0m     \u001b[38;5;66;03m# File, but it doesn't exist.\u001b[39;00m\n\u001b[0;32m-> 1861\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfile \u001b[39m\u001b[38;5;132;01m{\u001b[39;00murl_or_filename\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m not found\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m   1862\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1863\u001b[0m     \u001b[38;5;66;03m# Something unknown\u001b[39;00m\n",
-      "\u001b[0;31mOSError\u001b[0m: file ./config.json not found",
-      "\nDuring handling of the above exception, another exception occurred:\n",
-      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
-      "Input \u001b[0;32mIn [1]\u001b[0m, in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoProcessor\n\u001b[0;32m----> 3\u001b[0m processor \u001b[38;5;241m=\u001b[39m \u001b[43mAutoProcessor\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m./\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/models/auto/processing_auto.py:178\u001b[0m, in \u001b[0;36mAutoProcessor.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    176\u001b[0m \u001b[38;5;66;03m# Otherwise, load config, if it can be loaded.\u001b[39;00m\n\u001b[1;32m    177\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(config, PretrainedConfig):\n\u001b[0;32m--> 178\u001b[0m     config \u001b[38;5;241m=\u001b[39m \u001b[43mAutoConfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    180\u001b[0m model_type \u001b[38;5;241m=\u001b[39m config_class_to_model_type(\u001b[38;5;28mtype\u001b[39m(config)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m)\n\u001b[1;32m    182\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mgetattr\u001b[39m(config, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mprocessor_class\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/models/auto/configuration_auto.py:617\u001b[0m, in \u001b[0;36mAutoConfig.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    615\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mname_or_path\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m pretrained_model_name_or_path\n\u001b[1;32m    616\u001b[0m trust_remote_code \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtrust_remote_code\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mFalse\u001b[39;00m)\n\u001b[0;32m--> 617\u001b[0m config_dict, _ \u001b[38;5;241m=\u001b[39m \u001b[43mPretrainedConfig\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    618\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto_map\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAutoConfig\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mauto_map\u001b[39m\u001b[38;5;124m\"\u001b[39m]:\n\u001b[1;32m    619\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m trust_remote_code:\n",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:537\u001b[0m, in \u001b[0;36mPretrainedConfig.get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    535\u001b[0m original_kwargs \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mdeepcopy(kwargs)\n\u001b[1;32m    536\u001b[0m \u001b[38;5;66;03m# Get config dict associated with the base config file\u001b[39;00m\n\u001b[0;32m--> 537\u001b[0m config_dict, kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mcls\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_config_dict\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    539\u001b[0m \u001b[38;5;66;03m# That config file may point us toward another config file to use.\u001b[39;00m\n\u001b[1;32m    540\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mconfiguration_files\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m config_dict:\n",
-      "File \u001b[0;32m/opt/conda/lib/python3.8/site-packages/transformers/configuration_utils.py:626\u001b[0m, in \u001b[0;36mPretrainedConfig._get_config_dict\u001b[0;34m(cls, pretrained_model_name_or_path, **kwargs)\u001b[0m\n\u001b[1;32m    624\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n\u001b[1;32m    625\u001b[0m     logger\u001b[38;5;241m.\u001b[39merror(err)\n\u001b[0;32m--> 626\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m    627\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCan\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt load config for \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m. If you were trying to load it from \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    628\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m, make sure you don\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt have a local directory with the same name. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    629\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mOtherwise, make sure \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpretrained_model_name_or_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m is the correct path to a directory \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    630\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcontaining a \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mconfiguration_file\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m file\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    631\u001b[0m     )\n\u001b[1;32m    633\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    634\u001b[0m     \u001b[38;5;66;03m# Load config dict\u001b[39;00m\n\u001b[1;32m    635\u001b[0m     config_dict \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mcls\u001b[39m\u001b[38;5;241m.\u001b[39m_dict_from_json_file(resolved_config_file)\n",
-      "\u001b[0;31mOSError\u001b[0m: Can't load config for './'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure './' is the correct path to a directory containing a config.json file"
-     ]
-    }
-   ],
-   "source": [
-    "from transformers import AutoProcessor\n",
-    "\n",
-    "processor = AutoProcessor.from_pretrained(\"./\")"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "ab24f645",
-   "metadata": {},
-   "outputs": [],
-   "source": []
-  }
- ],
- "metadata": {
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.8.8"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 5
-}

.ipynb_checkpoints/eval-checkpoint.py

@@ -1,128 +0,0 @@
-#!/usr/bin/env python3
-import argparse
-import re
-from typing import Dict
-
-from datasets import Audio, Dataset, load_dataset, load_metric
-
-from transformers import AutoFeatureExtractor, pipeline
-
-
-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."""
-
-    chars_to_ignore_regex = '[^a-zàâäçéèêëîïôöùûüÿ\'’ ]'  # noqa: W605 IMPORTANT: this should correspond to the chars that were ignored during training
-
-    text = re.sub(chars_to_ignore_regex, "", text.lower()).replace('’', "'")
-
-    # In addition, we can normalize the target text, e.g. removing new lines characters etc...
-    # note that order is important here!
-    token_sequences_to_ignore = ["\n\n", "\n", "   ", "  "]
-
-    for t in token_sequences_to_ignore:
-        text = " ".join(text.split(t))
-
-    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 5 seconds."
-    )
-    parser.add_argument(
-        "--stride_length_s", type=float, default=None, help="Stride of the audio chunks. Defaults to 1 second."
-    )
-    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/mozilla-foundation_common_voice_8_0_fr_test_eval_results-checkpoint.txt

@@ -1,2 +0,0 @@
-WER: 0.18333515105245937
-CER: 0.05606368028384753

.ipynb_checkpoints/preprocessor_config-checkpoint.json

@@ -1,10 +0,0 @@
-{
-  "do_normalize": true,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0,
-  "processor_class": "Wav2Vec2ProcessorWithLM",
-  "return_attention_mask": true,
-  "sampling_rate": 16000
-}

.ipynb_checkpoints/run-checkpoint.sh

@@ -1,37 +0,0 @@
-export WANDB_PROJECT="xls-r-1b-cv_8-fr"
-python run_speech_recognition_ctc.py \
-    --activation_dropout="0.1" \
-    --dataset_name="mozilla-foundation/common_voice_8_0" \
-    --dataset_config_name="fr" \
-    --eval_steps="1000" \
-    --evaluation_strategy="steps" \
-    --feat_proj_dropout="0.0" \
-    --freeze_feature_encoder \
-    --fp16 \
-    --gradient_accumulation_steps="8" \
-    --gradient_checkpointing \
-    --group_by_length \
-    --layerdrop="0.0" \
-    --learning_rate="7.5e-5" \
-    --length_column_name="input_length" \
-    --load_best_model_at_end \
-    --logging_steps="100" \
-    --mask_feature_length="64" \
-    --mask_feature_prob="0.25" \
-    --mask_time_length="10" \
-    --mask_time_prob="0.75" \
-    --model_name_or_path="./checkpoint-13000" \
-    --num_train_epochs="6.0" \
-    --output_dir="./" \
-    --overwrite_output_dir \
-    --per_device_train_batch_size="16" \
-    --per_device_eval_batch_size="16" \
-    --preprocessing_num_workers="4" \
-    --push_to_hub \
-    --report_to="wandb" \
-    --save_steps="1000" \
-    --save_total_limit="3" \
-    --text_column_name="sentence" \
-    --use_auth_token \
-    --warmup_steps="2000" \
-    --do_train --do_eval

.ipynb_checkpoints/run_speech_recognition_ctc-checkpoint.py

@@ -1,734 +0,0 @@
-#!/usr/bin/env python
-# coding=utf-8
-# Copyright 2021 The HuggingFace Inc. team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-
-""" Fine-tuning a 🤗 Transformers CTC model for automatic speech recognition"""
-
-import functools
-import json
-import logging
-import os
-import re
-import sys
-import warnings
-from dataclasses import dataclass, field
-from typing import Dict, List, Optional, Union
-
-import datasets
-import numpy as np
-import torch
-from datasets import DatasetDict, load_dataset, load_metric
-
-import transformers
-from transformers import (
-    AutoConfig,
-    AutoFeatureExtractor,
-    AutoModelForCTC,
-    AutoProcessor,
-    AutoTokenizer,
-    HfArgumentParser,
-    Trainer,
-    TrainingArguments,
-    Wav2Vec2Processor,
-    set_seed,
-)
-from transformers.trainer_utils import get_last_checkpoint, is_main_process
-from transformers.utils import check_min_version
-from transformers.utils.versions import require_version
-
-
-# Will error if the minimal version of Transformers is not installed. Remove at your own risks.
-check_min_version("4.16.0.dev0")
-
-require_version("datasets>=1.13.3", "To fix: pip install -r examples/pytorch/text-classification/requirements.txt")
-
-
-logger = logging.getLogger(__name__)
-
-
-def list_field(default=None, metadata=None):
-    return field(default_factory=lambda: default, metadata=metadata)
-
-
-@dataclass
-class ModelArguments:
-    """
-    Arguments pertaining to which model/config/tokenizer we are going to fine-tune from.
-    """
-
-    model_name_or_path: str = field(
-        metadata={"help": "Path to pretrained model or model identifier from huggingface.co/models"}
-    )
-    tokenizer_name_or_path: Optional[str] = field(
-        default=None,
-        metadata={"help": "Path to pretrained tokenizer or tokenizer identifier from huggingface.co/models"},
-    )
-    cache_dir: Optional[str] = field(
-        default=None,
-        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
-    )
-    freeze_feature_encoder: bool = field(
-        default=True, metadata={"help": "Whether to freeze the feature encoder layers of the model."}
-    )
-    attention_dropout: float = field(
-        default=0.0, metadata={"help": "The dropout ratio for the attention probabilities."}
-    )
-    activation_dropout: float = field(
-        default=0.0, metadata={"help": "The dropout ratio for activations inside the fully connected layer."}
-    )
-    feat_proj_dropout: float = field(default=0.0, metadata={"help": "The dropout ratio for the projected features."})
-    hidden_dropout: float = field(
-        default=0.0,
-        metadata={
-            "help": "The dropout probability for all fully connected layers in the embeddings, encoder, and pooler."
-        },
-    )
-    final_dropout: float = field(
-        default=0.0,
-        metadata={"help": "The dropout probability for the final projection layer."},
-    )
-    mask_time_prob: float = field(
-        default=0.05,
-        metadata={
-            "help": "Probability of each feature vector along the time axis to be chosen as the start of the vector"
-            "span to be masked. Approximately ``mask_time_prob * sequence_length // mask_time_length`` feature"
-            "vectors will be masked along the time axis."
-        },
-    )
-    mask_time_length: int = field(
-        default=10,
-        metadata={"help": "Length of vector span to mask along the time axis."},
-    )
-    mask_feature_prob: float = field(
-        default=0.0,
-        metadata={
-            "help": "Probability of each feature vector along the feature axis to be chosen as the start of the vector"
-            "span to be masked. Approximately ``mask_feature_prob * sequence_length // mask_feature_length`` feature bins will be masked along the time axis."
-        },
-    )
-    mask_feature_length: int = field(
-        default=10,
-        metadata={"help": "Length of vector span to mask along the feature axis."},
-    )
-    layerdrop: float = field(default=0.0, metadata={"help": "The LayerDrop probability."})
-    ctc_loss_reduction: Optional[str] = field(
-        default="mean", metadata={"help": "The way the ctc loss should be reduced. Should be one of 'mean' or 'sum'."}
-    )
-
-
-@dataclass
-class DataTrainingArguments:
-    """
-    Arguments pertaining to what data we are going to input our model for training and eval.
-
-    Using `HfArgumentParser` we can turn this class
-    into argparse arguments to be able to specify them on
-    the command line.
-    """
-
-    dataset_name: str = field(
-        metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
-    )
-    dataset_config_name: str = field(
-        default=None, metadata={"help": "The configuration name of the dataset to use (via the datasets library)."}
-    )
-    train_split_name: str = field(
-        default="train+validation",
-        metadata={
-            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'train'"
-        },
-    )
-    eval_split_name: str = field(
-        default="test",
-        metadata={
-            "help": "The name of the training data set split to use (via the datasets library). Defaults to 'test'"
-        },
-    )
-    audio_column_name: str = field(
-        default="audio",
-        metadata={"help": "The name of the dataset column containing the audio data. Defaults to 'audio'"},
-    )
-    text_column_name: str = field(
-        default="text",
-        metadata={"help": "The name of the dataset column containing the text data. Defaults to 'text'"},
-    )
-    overwrite_cache: bool = field(
-        default=False, metadata={"help": "Overwrite the cached preprocessed datasets or not."}
-    )
-    preprocessing_num_workers: Optional[int] = field(
-        default=None,
-        metadata={"help": "The number of processes to use for the preprocessing."},
-    )
-    max_train_samples: Optional[int] = field(
-        default=None,
-        metadata={
-            "help": "For debugging purposes or quicker training, truncate the number of training examples to this "
-            "value if set."
-        },
-    )
-    max_eval_samples: Optional[int] = field(
-        default=None,
-        metadata={
-            "help": "For debugging purposes or quicker training, truncate the number of validation examples to this "
-            "value if set."
-        },
-    )
-    chars_to_ignore: Optional[List[str]] = list_field(
-        default=None,
-        metadata={"help": "A list of characters to remove from the transcripts."},
-    )
-    eval_metrics: List[str] = list_field(
-        default=["wer"],
-        metadata={"help": "A list of metrics the model should be evaluated on. E.g. `'wer cer'`"},
-    )
-    max_duration_in_seconds: float = field(
-        default=20.0,
-        metadata={
-            "help": "Filter audio files that are longer than `max_duration_in_seconds` seconds to 'max_duration_in_seconds`"
-        },
-    )
-    min_duration_in_seconds: float = field(
-        default=0.0, metadata={"help": "Filter audio files that are shorter than `min_duration_in_seconds` seconds"}
-    )
-    preprocessing_only: bool = field(
-        default=False,
-        metadata={
-            "help": "Whether to only do data preprocessing and skip training. "
-            "This is especially useful when data preprocessing errors out in distributed training due to timeout. "
-            "In this case, one should run the preprocessing in a non-distributed setup with `preprocessing_only=True` "
-            "so that the cached datasets can consequently be loaded in distributed training"
-        },
-    )
-    use_auth_token: bool = field(
-        default=False,
-        metadata={
-            "help": "If :obj:`True`, will use the token generated when running"
-            ":obj:`transformers-cli login` as HTTP bearer authorization for remote files."
-        },
-    )
-    unk_token: str = field(
-        default="[UNK]",
-        metadata={"help": "The unk token for the tokenizer"},
-    )
-    pad_token: str = field(
-        default="[PAD]",
-        metadata={"help": "The padding token for the tokenizer"},
-    )
-    word_delimiter_token: str = field(
-        default="|",
-        metadata={"help": "The word delimiter token for the tokenizer"},
-    )
-    phoneme_language: Optional[str] = field(
-        default=None,
-        metadata={
-            "help": "The target language that should be used be"
-            " passed to the tokenizer for tokenization. Note that"
-            " this is only relevant if the model classifies the"
-            " input audio to a sequence of phoneme sequences."
-        },
-    )
-
-
-@dataclass
-class DataCollatorCTCWithPadding:
-    """
-    Data collator that will dynamically pad the inputs received.
-    Args:
-        processor (:class:`~transformers.AutoProcessor`)
-            The processor used for proccessing the data.
-        padding (:obj:`bool`, :obj:`str` or :class:`~transformers.tokenization_utils_base.PaddingStrategy`, `optional`, defaults to :obj:`True`):
-            Select a strategy to pad the returned sequences (according to the model's padding side and padding index)
-            among:
-            * :obj:`True` or :obj:`'longest'`: Pad to the longest sequence in the batch (or no padding if only a single
-              sequence if provided).
-            * :obj:`'max_length'`: Pad to a maximum length specified with the argument :obj:`max_length` or to the
-              maximum acceptable input length for the model if that argument is not provided.
-            * :obj:`False` or :obj:`'do_not_pad'` (default): No padding (i.e., can output a batch with sequences of
-              different lengths).
-        max_length (:obj:`int`, `optional`):
-            Maximum length of the ``input_values`` of the returned list and optionally padding length (see above).
-        max_length_labels (:obj:`int`, `optional`):
-            Maximum length of the ``labels`` returned list and optionally padding length (see above).
-        pad_to_multiple_of (:obj:`int`, `optional`):
-            If set will pad the sequence to a multiple of the provided value.
-            This is especially useful to enable the use of Tensor Cores on NVIDIA hardware with compute capability >=
-            7.5 (Volta).
-    """
-
-    processor: AutoProcessor
-    padding: Union[bool, str] = "longest"
-    pad_to_multiple_of: Optional[int] = None
-    pad_to_multiple_of_labels: Optional[int] = None
-
-    def __call__(self, features: List[Dict[str, Union[List[int], torch.Tensor]]]) -> Dict[str, torch.Tensor]:
-        # split inputs and labels since they have to be of different lenghts and need
-        # different padding methods
-        input_features = [{"input_values": feature["input_values"]} for feature in features]
-        label_features = [{"input_ids": feature["labels"]} for feature in features]
-
-        batch = self.processor.pad(
-            input_features,
-            padding=self.padding,
-            pad_to_multiple_of=self.pad_to_multiple_of,
-            return_tensors="pt",
-        )
-
-        with self.processor.as_target_processor():
-            labels_batch = self.processor.pad(
-                label_features,
-                padding=self.padding,
-                pad_to_multiple_of=self.pad_to_multiple_of_labels,
-                return_tensors="pt",
-            )
-
-        # replace padding with -100 to ignore loss correctly
-        labels = labels_batch["input_ids"].masked_fill(labels_batch.attention_mask.ne(1), -100)
-
-        batch["labels"] = labels
-
-        return batch
-
-
-def create_vocabulary_from_data(
-    datasets: DatasetDict,
-    word_delimiter_token: Optional[str] = None,
-    unk_token: Optional[str] = None,
-    pad_token: Optional[str] = None,
-):
-    # Given training and test labels create vocabulary
-    def extract_all_chars(batch):
-        all_text = " ".join(batch["target_text"])
-        vocab = list(set(all_text))
-        return {"vocab": [vocab], "all_text": [all_text]}
-
-    vocabs = datasets.map(
-        extract_all_chars,
-        batched=True,
-        batch_size=-1,
-        keep_in_memory=True,
-        remove_columns=datasets["train"].column_names,
-    )
-
-    # take union of all unique characters in each dataset
-    vocab_set = functools.reduce(
-        lambda vocab_1, vocab_2: set(vocab_1["vocab"][0]) | set(vocab_2["vocab"][0]), vocabs.values()
-    )
-
-    vocab_dict = {v: k for k, v in enumerate(sorted(list(vocab_set)))}
-
-    # replace white space with delimiter token
-    if word_delimiter_token is not None:
-        vocab_dict[word_delimiter_token] = vocab_dict[" "]
-        del vocab_dict[" "]
-
-    # add unk and pad token
-    if unk_token is not None:
-        vocab_dict[unk_token] = len(vocab_dict)
-
-    if pad_token is not None:
-        vocab_dict[pad_token] = len(vocab_dict)
-
-    return vocab_dict
-
-
-def main():
-    # See all possible arguments in src/transformers/training_args.py
-    # or by passing the --help flag to this script.
-    # We now keep distinct sets of args, for a cleaner separation of concerns.
-
-    parser = HfArgumentParser((ModelArguments, DataTrainingArguments, TrainingArguments))
-    if len(sys.argv) == 2 and sys.argv[1].endswith(".json"):
-        # If we pass only one argument to the script and it's the path to a json file,
-        # let's parse it to get our arguments.
-        model_args, data_args, training_args = parser.parse_json_file(json_file=os.path.abspath(sys.argv[1]))
-    else:
-        model_args, data_args, training_args = parser.parse_args_into_dataclasses()
-
-    # Detecting last checkpoint.
-    last_checkpoint = None
-    if os.path.isdir(training_args.output_dir) and training_args.do_train and not training_args.overwrite_output_dir:
-        last_checkpoint = get_last_checkpoint(training_args.output_dir)
-        if last_checkpoint is None and len(os.listdir(training_args.output_dir)) > 0:
-            raise ValueError(
-                f"Output directory ({training_args.output_dir}) already exists and is not empty. "
-                "Use --overwrite_output_dir to overcome."
-            )
-        elif last_checkpoint is not None:
-            logger.info(
-                f"Checkpoint detected, resuming training at {last_checkpoint}. To avoid this behavior, change "
-                "the `--output_dir` or add `--overwrite_output_dir` to train from scratch."
-            )
-
-    # Setup logging
-    logging.basicConfig(
-        format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
-        datefmt="%m/%d/%Y %H:%M:%S",
-        handlers=[logging.StreamHandler(sys.stdout)],
-    )
-    logger.setLevel(logging.INFO if is_main_process(training_args.local_rank) else logging.WARN)
-
-    # Log on each process the small summary:
-    logger.warning(
-        f"Process rank: {training_args.local_rank}, device: {training_args.device}, n_gpu: {training_args.n_gpu}"
-        f"distributed training: {bool(training_args.local_rank != -1)}, 16-bits training: {training_args.fp16}"
-    )
-    # Set the verbosity to info of the Transformers logger (on main process only):
-    if is_main_process(training_args.local_rank):
-        transformers.utils.logging.set_verbosity_info()
-    logger.info("Training/evaluation parameters %s", training_args)
-
-    # Set seed before initializing model.
-    set_seed(training_args.seed)
-
-    # 1. First, let's load the dataset
-    raw_datasets = DatasetDict()
-
-    if training_args.do_train:
-        raw_datasets["train"] = load_dataset(
-            data_args.dataset_name,
-            data_args.dataset_config_name,
-            split=data_args.train_split_name,
-            use_auth_token=data_args.use_auth_token,
-        )
-
-        if data_args.audio_column_name not in raw_datasets["train"].column_names:
-            raise ValueError(
-                f"--audio_column_name '{data_args.audio_column_name}' not found in dataset '{data_args.dataset_name}'. "
-                "Make sure to set `--audio_column_name` to the correct audio column - one of "
-                f"{', '.join(raw_datasets['train'].column_names)}."
-            )
-
-        if data_args.text_column_name not in raw_datasets["train"].column_names:
-            raise ValueError(
-                f"--text_column_name {data_args.text_column_name} not found in dataset '{data_args.dataset_name}'. "
-                "Make sure to set `--text_column_name` to the correct text column - one of "
-                f"{', '.join(raw_datasets['train'].column_names)}."
-            )
-
-        if data_args.max_train_samples is not None:
-            raw_datasets["train"] = raw_datasets["train"].select(range(data_args.max_train_samples))
-
-    if training_args.do_eval:
-        raw_datasets["eval"] = load_dataset(
-            data_args.dataset_name,
-            data_args.dataset_config_name,
-            split=data_args.eval_split_name,
-            use_auth_token=data_args.use_auth_token,
-        )
-
-        if data_args.max_eval_samples is not None:
-            raw_datasets["eval"] = raw_datasets["eval"].select(range(data_args.max_eval_samples))
-
-    # 2. We remove some special characters from the datasets
-    # that make training complicated and do not help in transcribing the speech
-    # E.g. characters, such as `,` and `.` do not really have an acoustic characteristic
-    # that could be easily picked up by the model
-    chars_to_ignore_regex = '[^a-zàâäçéèêëîïôöùûüÿ\'’ ]'
-    text_column_name = data_args.text_column_name
-
-    def remove_and_replace_special_characters(batch):
-        batch["target_text"] = re.sub(chars_to_ignore_regex, "", batch[text_column_name].lower()).replace('’', "'") + " "
-        return batch
-
-    with training_args.main_process_first(desc="dataset map special characters removal"):
-        raw_datasets = raw_datasets.map(
-            remove_and_replace_special_characters,
-            remove_columns=[text_column_name],
-            desc="remove special characters from datasets",
-        )
-
-    # save special tokens for tokenizer
-    word_delimiter_token = data_args.word_delimiter_token
-    unk_token = data_args.unk_token
-    pad_token = data_args.pad_token
-
-    # 3. Next, let's load the config as we might need it to create
-    # the tokenizer
-    # load config
-    config = AutoConfig.from_pretrained(
-        model_args.model_name_or_path, cache_dir=model_args.cache_dir, use_auth_token=data_args.use_auth_token
-    )
-
-    # 4. Next, if no tokenizer file is defined,
-    # we create the vocabulary of the model by extracting all unique characters from
-    # the training and evaluation datasets
-    # We need to make sure that only first rank saves vocabulary
-    # make sure all processes wait until vocab is created
-    tokenizer_name_or_path = model_args.tokenizer_name_or_path
-    tokenizer_kwargs = {}
-    if tokenizer_name_or_path is None:
-        # save vocab in training output dir
-        tokenizer_name_or_path = training_args.output_dir
-
-        vocab_file = os.path.join(tokenizer_name_or_path, "vocab.json")
-
-        with training_args.main_process_first():
-            if training_args.overwrite_output_dir and os.path.isfile(vocab_file):
-                os.remove(vocab_file)
-
-        with training_args.main_process_first(desc="dataset map vocabulary creation"):
-            if not os.path.isfile(vocab_file):
-                os.makedirs(tokenizer_name_or_path, exist_ok=True)
-                vocab_dict = create_vocabulary_from_data(
-                    raw_datasets,
-                    word_delimiter_token=word_delimiter_token,
-                    unk_token=unk_token,
-                    pad_token=pad_token,
-                )
-
-                # save vocab dict to be loaded into tokenizer
-                with open(vocab_file, "w") as file:
-                    json.dump(vocab_dict, file)
-
-        # if tokenizer has just been created
-        # it is defined by `tokenizer_class` if present in config else by `model_type`
-        tokenizer_kwargs = {
-            "config": config if config.tokenizer_class is not None else None,
-            "tokenizer_type": config.model_type if config.tokenizer_class is None else None,
-            "unk_token": unk_token,
-            "pad_token": pad_token,
-            "eos_token": None,
-            "bos_token": None,
-            "word_delimiter_token": word_delimiter_token,
-        }
-
-    # 5. Now we can instantiate the feature extractor, tokenizer and model
-    # Note for distributed training, the .from_pretrained methods guarantee that only
-    # one local process can concurrently download model & vocab.
-
-    # load feature_extractor and tokenizer
-    tokenizer = AutoTokenizer.from_pretrained(
-        tokenizer_name_or_path,
-        use_auth_token=data_args.use_auth_token,
-        **tokenizer_kwargs,
-    )
-    feature_extractor = AutoFeatureExtractor.from_pretrained(
-        model_args.model_name_or_path, cache_dir=model_args.cache_dir, use_auth_token=data_args.use_auth_token
-    )
-
-    # adapt config
-    config.update(
-        {
-            "feat_proj_dropout": model_args.feat_proj_dropout,
-            "attention_dropout": model_args.attention_dropout,
-            "hidden_dropout": model_args.hidden_dropout,
-            "final_dropout": model_args.final_dropout,
-            "mask_time_prob": model_args.mask_time_prob,
-            "mask_time_length": model_args.mask_time_length,
-            "mask_feature_prob": model_args.mask_feature_prob,
-            "mask_feature_length": model_args.mask_feature_length,
-            "gradient_checkpointing": training_args.gradient_checkpointing,
-            "layerdrop": model_args.layerdrop,
-            "ctc_loss_reduction": model_args.ctc_loss_reduction,
-            "pad_token_id": tokenizer.pad_token_id,
-            "vocab_size": len(tokenizer),
-            "activation_dropout": model_args.activation_dropout,
-        }
-    )
-
-    # create model
-    model = AutoModelForCTC.from_pretrained(
-        model_args.model_name_or_path,
-        cache_dir=model_args.cache_dir,
-        config=config,
-        use_auth_token=data_args.use_auth_token,
-    )
-
-    # freeze encoder
-    if model_args.freeze_feature_encoder:
-        model.freeze_feature_encoder()
-
-    # 6. Now we preprocess the datasets including loading the audio, resampling and normalization
-    # Thankfully, `datasets` takes care of automatically loading and resampling the audio,
-    # so that we just need to set the correct target sampling rate and normalize the input
-    # via the `feature_extractor`
-
-    # make sure that dataset decodes audio with correct sampling rate
-    dataset_sampling_rate = next(iter(raw_datasets.values())).features[data_args.audio_column_name].sampling_rate
-    if dataset_sampling_rate != feature_extractor.sampling_rate:
-        raw_datasets = raw_datasets.cast_column(
-            data_args.audio_column_name, datasets.features.Audio(sampling_rate=feature_extractor.sampling_rate)
-        )
-
-    # derive max & min input length for sample rate & max duration
-    max_input_length = data_args.max_duration_in_seconds * feature_extractor.sampling_rate
-    min_input_length = data_args.min_duration_in_seconds * feature_extractor.sampling_rate
-    audio_column_name = data_args.audio_column_name
-    num_workers = data_args.preprocessing_num_workers
-
-    # `phoneme_language` is only relevant if the model is fine-tuned on phoneme classification
-    phoneme_language = data_args.phoneme_language
-
-    # Preprocessing the datasets.
-    # We need to read the audio files as arrays and tokenize the targets.
-    def prepare_dataset(batch):
-        # load audio
-        sample = batch[audio_column_name]
-
-        inputs = feature_extractor(sample["array"], sampling_rate=sample["sampling_rate"])
-        batch["input_values"] = inputs.input_values[0]
-        batch["input_length"] = len(batch["input_values"])
-
-        # encode targets
-        additional_kwargs = {}
-        if phoneme_language is not None:
-            additional_kwargs["phonemizer_lang"] = phoneme_language
-
-        batch["labels"] = tokenizer(batch["target_text"], **additional_kwargs).input_ids
-        return batch
-
-    with training_args.main_process_first(desc="dataset map preprocessing"):
-        vectorized_datasets = raw_datasets.map(
-            prepare_dataset,
-            remove_columns=next(iter(raw_datasets.values())).column_names,
-            num_proc=num_workers,
-            desc="preprocess datasets",
-        )
-
-        def is_audio_in_length_range(length):
-            return length > min_input_length and length < max_input_length
-
-        # filter data that is shorter than min_input_length
-        vectorized_datasets = vectorized_datasets.filter(
-            is_audio_in_length_range,
-            num_proc=num_workers,
-            input_columns=["input_length"],
-        )
-
-    # 7. Next, we can prepare the training.
-    # Let's use word error rate (WER) as our evaluation metric,
-    # instantiate a data collator and the trainer
-
-    # Define evaluation metrics during training, *i.e.* word error rate, character error rate
-    eval_metrics = {metric: load_metric(metric) for metric in data_args.eval_metrics}
-
-    # for large datasets it is advised to run the preprocessing on a
-    # single machine first with ``args.preprocessing_only`` since there will mostly likely
-    # be a timeout when running the script in distributed mode.
-    # In a second step ``args.preprocessing_only`` can then be set to `False` to load the
-    # cached dataset
-    if data_args.preprocessing_only:
-        logger.info(f"Data preprocessing finished. Files cached at {vectorized_datasets.cache_files}")
-        return
-
-    def compute_metrics(pred):
-        pred_logits = pred.predictions
-        pred_ids = np.argmax(pred_logits, axis=-1)
-
-        pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
-
-        pred_str = tokenizer.batch_decode(pred_ids)
-        # we do not want to group tokens when computing the metrics
-        label_str = tokenizer.batch_decode(pred.label_ids, group_tokens=False)
-
-        metrics = {k: v.compute(predictions=pred_str, references=label_str) for k, v in eval_metrics.items()}
-
-        return metrics
-
-    # Now save everything to be able to create a single processor later
-    if is_main_process(training_args.local_rank):
-        # save feature extractor, tokenizer and config
-        feature_extractor.save_pretrained(training_args.output_dir)
-        tokenizer.save_pretrained(training_args.output_dir)
-        config.save_pretrained(training_args.output_dir)
-
-    try:
-        processor = AutoProcessor.from_pretrained(training_args.output_dir)
-    except (OSError, KeyError):
-        warnings.warn(
-            "Loading a processor from a feature extractor config that does not"
-            " include a `processor_class` attribute is deprecated and will be removed in v5. Please add the following "
-            " attribute to your `preprocessor_config.json` file to suppress this warning: "
-            " `'processor_class': 'Wav2Vec2Processor'`",
-            FutureWarning,
-        )
-        processor = Wav2Vec2Processor.from_pretrained(training_args.output_dir)
-
-    # Instantiate custom data collator
-    data_collator = DataCollatorCTCWithPadding(processor=processor)
-
-    # Initialize Trainer
-    trainer = Trainer(
-        model=model,
-        data_collator=data_collator,
-        args=training_args,
-        compute_metrics=compute_metrics,
-        train_dataset=vectorized_datasets["train"] if training_args.do_train else None,
-        eval_dataset=vectorized_datasets["eval"] if training_args.do_eval else None,
-        tokenizer=feature_extractor,
-    )
-
-    # 8. Finally, we can start training
-
-    # Training
-    if training_args.do_train:
-
-        # use last checkpoint if exist
-        if last_checkpoint is not None:
-            checkpoint = last_checkpoint
-        elif os.path.isdir(model_args.model_name_or_path):
-            checkpoint = model_args.model_name_or_path
-        else:
-            checkpoint = None
-
-        train_result = trainer.train(resume_from_checkpoint=checkpoint)
-        trainer.save_model()
-
-        metrics = train_result.metrics
-        max_train_samples = (
-            data_args.max_train_samples
-            if data_args.max_train_samples is not None
-            else len(vectorized_datasets["train"])
-        )
-        metrics["train_samples"] = min(max_train_samples, len(vectorized_datasets["train"]))
-
-        trainer.log_metrics("train", metrics)
-        trainer.save_metrics("train", metrics)
-        trainer.save_state()
-
-    # Evaluation
-    results = {}
-    if training_args.do_eval:
-        logger.info("*** Evaluate ***")
-        metrics = trainer.evaluate()
-        max_eval_samples = (
-            data_args.max_eval_samples if data_args.max_eval_samples is not None else len(vectorized_datasets["eval"])
-        )
-        metrics["eval_samples"] = min(max_eval_samples, len(vectorized_datasets["eval"]))
-
-        trainer.log_metrics("eval", metrics)
-        trainer.save_metrics("eval", metrics)
-
-    # Write model card and (optionally) push to hub
-    config_name = data_args.dataset_config_name if data_args.dataset_config_name is not None else "na"
-    kwargs = {
-        "finetuned_from": model_args.model_name_or_path,
-        "tasks": "speech-recognition",
-        "tags": ["automatic-speech-recognition", data_args.dataset_name],
-        "dataset_args": f"Config: {config_name}, Training split: {data_args.train_split_name}, Eval split: {data_args.eval_split_name}",
-        "dataset": f"{data_args.dataset_name.upper()} - {config_name.upper()}",
-    }
-    if "common_voice" in data_args.dataset_name:
-        kwargs["language"] = config_name
-
-    if training_args.push_to_hub:
-        trainer.push_to_hub(**kwargs)
-    else:
-        trainer.create_model_card(**kwargs)
-
-    return results
-
-
-if __name__ == "__main__":
-    main()

.ipynb_checkpoints/speech-recognition-community-v2_dev_data_fr_validation_eval_results-checkpoint.txt

@@ -1,2 +0,0 @@
-WER: 0.6024801374275285
-CER: 0.15675326436359865

.ipynb_checkpoints/train_results-checkpoint.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 4.0,
-    "train_loss": 0.9901066277552089,
-    "train_runtime": 182144.7146,
-    "train_samples": 446485,
-    "train_samples_per_second": 9.805,
-    "train_steps_per_second": 0.077
-}

trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": Infinity,
-  "best_model_checkpoint": "./checkpoint-1000",
+  "best_model_checkpoint": "./checkpoint-13000",
   "epoch": 5.999928330824912,
   "global_step": 20928,
   "is_hyper_param_search": false,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48a427c7cb614f5fbcb1a4088c5c4abce496c5c8b09e2e526d99a2586ab2194
+oid sha256:af168053e52049b75214ffe031549b7a5ed7c0e774b3f727dc7f6c7d61dd0f9c
 size 2991