updated philipps config

Algo-Boys · Sep 18, 2023 · 27ce3de · 27ce3de
1 parent f6e6377
commit 27ce3de
Show file tree

Hide file tree

Showing 2 changed files with 11 additions and 70 deletions.
diff --git a/config.philipp.yaml b/config.philipp.yaml
@@ -18,17 +18,17 @@ tokenizer:
   tokenizer_path: "data/tokenizers/char_tokenizer_german.json"
 
 decoder:
-  type: "greedy" # greedy, or lm (beam search)
+  type: "lm" # greedy, or lm (beam search)
 
   lm: # config for lm decoder
     language_model_path: "data" # path where model and supplementary files are stored
     language: "german"
-    n_gram: 3 # n-gram size of the language model, 3 or 5
-    beam_size: 50 
-    beam_threshold: 50
+    n_gram: 5 # n-gram size of the language model, 3 or 5
+    beam_size: 500 
+    beam_threshold: 150
     n_best: 1
-    lm_weight: 2
-    word_score: 0
+    lm_weight: 5
+    word_score: -1
 
 training:
   learning_rate: 0.0005

diff --git a/lm_decoder_hparams.ipynb b/lm_decoder_hparams.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -15,20 +15,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/var/folders/lm/1zmdkgm91k912l2vgq978z800000gn/T/ipykernel_80481/3805229751.py:1: TqdmExperimentalWarning: Using `tqdm.autonotebook.tqdm` in notebook mode. Use `tqdm.tqdm` instead to force console mode (e.g. in jupyter console)\n",
-      "  from tqdm.autonotebook import tqdm\n",
-      "/Users/philippmerkel/DEV/SWR2-cool-projekt/.venv/lib/python3.10/site-packages/torchaudio/models/decoder/_ctc_decoder.py:62: UserWarning: The built-in flashlight integration is deprecated, and will be removed in future release. Please install flashlight-text. https://pypi.org/project/flashlight-text/ For the detail of CTC decoder migration, please see https://github.com/pytorch/audio/issues/3088.\n",
-      "  warnings.warn(\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "from tqdm.autonotebook import tqdm\n",
     "\n",
@@ -45,57 +34,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "application/vnd.jupyter.widget-view+json": {
-       "model_id": "34aafd9aca2541748dc41d8550334536",
-       "version_major": 2,
-       "version_minor": 0
-      },
-      "text/plain": [
-       "  0%|          | 0/144 [00:00<?, ?it/s]"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Download flag not set, skipping download\n"
-     ]
-    },
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "/Users/philippmerkel/DEV/SWR2-cool-projekt/.venv/lib/python3.10/site-packages/torchaudio/functional/functional.py:576: UserWarning: At least one mel filterbank has all zero values. The value for `n_mels` (128) may be set too high. Or, the value for `n_freqs` (201) may be set too low.\n",
-      "  warnings.warn(\n"
-     ]
-    },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "New best WER:  0.8266228565397248  CER:  0.6048691547202959\n",
-      "Config:  {'language': 'german', 'language_model_path': 'data', 'n_gram': 3, 'beam_size': 25, 'beam_threshold': 10, 'n_best': 1, 'lm_weight': 0, 'word_score': -1.5, 'beam_size_token': 10}\n",
-      "LM Weight:  0  Word Score:  -1.5  Beam Size:  25  Beam Threshold:  10  Beam Size Token:  10\n",
-      "--------------------------------------------------------------\n",
-      "New best WER:  0.7900706123452581  CER:  0.49197597466135945\n",
-      "Config:  {'language': 'german', 'language_model_path': 'data', 'n_gram': 3, 'beam_size': 25, 'beam_threshold': 50, 'n_best': 1, 'lm_weight': 0, 'word_score': -1.5, 'beam_size_token': 10}\n",
-      "LM Weight:  0  Word Score:  -1.5  Beam Size:  25  Beam Threshold:  50  Beam Size Token:  10\n",
-      "--------------------------------------------------------------\n",
-      "New best WER:  0.7877685082828738  CER:  0.48660732878914315\n",
-      "Config:  {'language': 'german', 'language_model_path': 'data', 'n_gram': 3, 'beam_size': 100, 'beam_threshold': 50, 'n_best': 1, 'lm_weight': 0, 'word_score': -1.5, 'beam_size_token': 10}\n",
-      "LM Weight:  0  Word Score:  -1.5  Beam Size:  100  Beam Threshold:  50  Beam Size Token:  10\n",
-      "--------------------------------------------------------------\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "\n",
     "\n",