Merge pull request #28 from ieasybooks/use_multiple_wit_keys

Use multiple wit.ai API keys to transcript the same video

.github/workflows/formatter.yml

@@ -22,4 +22,4 @@ jobs:
       - name: isort formatter
         uses: isort/isort-action@v1
         with:
-          configuration: "--profile black --check-only --diff --line-length 120"
+          configuration: "--profile black --src tafrigh --line-length 120 --lines-between-types 1 --lines-after-imports 2 --case-sensitive --trailing-comma --check-only --diff"

.pre-commit-config.yaml

@@ -0,0 +1,42 @@
+---
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.3.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-ast
+      - id: check-builtin-literals
+      - id: check-case-conflict
+      - id: check-docstring-first
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-vcs-permalinks
+      - id: check-xml
+      - id: check-yaml
+      - id: debug-statements
+      - id: destroyed-symlinks
+      - id: detect-private-key
+      - id: end-of-file-fixer
+        types: [ python ]
+      - id: fix-byte-order-marker
+      - id: mixed-line-ending
+      - id: name-tests-test
+        args: [ --pytest-test-first ]
+      - id: trailing-whitespace
+        types: [ python ]
+
+  - repo: https://github.com/psf/black
+    rev: 23.7.0
+    hooks:
+      - id: black
+        additional_dependencies: [click==8.0.4]
+
+  - repo: https://github.com/PyCQA/isort
+    rev: 5.12.0
+    hooks:
+      - id: isort

README.md

@@ -113,7 +113,7 @@
   <li>
     خيارات تقنية Wit
     <ul dir="rtl">
-      <li>مفتاح <a href="wit.ai">wit.ai</a>: يمكنك استخدام تقنيات <a href="wit.ai">wit.ai</a> لتفريغ المواد إلى نصوص من خلال تمرير المفتاح الخاص بك للاختيار <code dir="ltr">--wit_client_access_token</code>. إذا تم تمرير هذا الاختيار، سيتم استخدام <a href="wit.ai">wit.ai</a> لتفريغ المواد إلى نصوص. غير ذلك، سيتم استخدام نماذج Whisper</li>
+      <li>مفاتيح <a href="wit.ai">wit.ai</a>: يمكنك استخدام تقنيات <a href="wit.ai">wit.ai</a> لتفريغ المواد إلى نصوص من خلال تمرير المفتاح أو المفاتيح الخاصة بك للاختيار <code dir="ltr">--wit_client_access_tokens</code>. إذا تم تمرير هذا الاختيار، سيتم استخدام <a href="wit.ai">wit.ai</a> لتفريغ المواد إلى نصوص. غير ذلك، سيتم استخدام نماذج Whisper</li>
       <li>تحديد أقصى مدة للتقطيع: يمكنك تحديد أقصى مدة للتقطيع والتي ستؤثر على طول الجمل في ملفات SRT و VTT من خلال تمرير الاختيار <code dir="ltr">--max_cutting_duration</code>. القيمة الافتراضية هي <code>15</code></li>
     </ul>
   </li>
@@ -145,8 +145,9 @@
 usage: tafrigh [-h] [--skip_if_output_exist | --no-skip_if_output_exist] [--playlist_items PLAYLIST_ITEMS] [--verbose | --no-verbose] [-m MODEL_NAME_OR_PATH] [-t {transcribe,translate}]
                [-l {af,am,ar,as,az,ba,be,bg,bn,bo,br,bs,ca,cs,cy,da,de,el,en,es,et,eu,fa,fi,fo,fr,gl,gu,ha,haw,he,hi,hr,ht,hu,hy,id,is,it,ja,jw,ka,kk,km,kn,ko,la,lb,ln,lo,lt,lv,mg,mi,mk,ml,mn,mr,ms,mt,my,ne,nl,nn,no,oc,pa,pl,ps,pt,ro,ru,sa,sd,si,sk,sl,sn,so,sq,sr,su,sv,sw,ta,te,tg,th,tk,tl,tr,tt,uk,ur,uz,vi,yi,yo,zh}]
                [--use_faster_whisper | --no-use_faster_whisper] [--use_whisper_jax | --no-use_whisper_jax] [--beam_size BEAM_SIZE] [--ct2_compute_type {default,int8,int8_float16,int16,float16}]
-               [-w WIT_CLIENT_ACCESS_TOKEN] [--max_cutting_duration [1-17]] [--min_words_per_segment MIN_WORDS_PER_SEGMENT] [--save_files_before_compact | --no-save_files_before_compact]
-               [--save_yt_dlp_responses | --no-save_yt_dlp_responses] [--output_sample OUTPUT_SAMPLE] [-f {all,txt,srt,vtt,none} [{all,txt,srt,vtt,none} ...]] [-o OUTPUT_DIR]
+               [-w WIT_CLIENT_ACCESS_TOKENS [WIT_CLIENT_ACCESS_TOKENS ...]] [--max_cutting_duration [1-17]] [--min_words_per_segment MIN_WORDS_PER_SEGMENT]
+               [--save_files_before_compact | --no-save_files_before_compact] [--save_yt_dlp_responses | --no-save_yt_dlp_responses] [--output_sample OUTPUT_SAMPLE]
+               [-f {all,txt,srt,vtt,none} [{all,txt,srt,vtt,none} ...]] [-o OUTPUT_DIR]
                urls_or_paths [urls_or_paths ...]
 
 options:
@@ -178,8 +179,8 @@ Whisper:
                         Quantization type applied while converting the model to CTranslate2 format.
 
 Wit:
-  -w WIT_CLIENT_ACCESS_TOKEN, --wit_client_access_token WIT_CLIENT_ACCESS_TOKEN
-                        wit.ai client access token. If provided, wit.ai APIs will be used to do the transcription, otherwise whisper will be used.
+  -w WIT_CLIENT_ACCESS_TOKENS [WIT_CLIENT_ACCESS_TOKENS ...], --wit_client_access_tokens WIT_CLIENT_ACCESS_TOKENS [WIT_CLIENT_ACCESS_TOKENS ...]
+                        List of wit.ai client access tokens. If provided, wit.ai APIs will be used to do the transcription, otherwise whisper will be used.
   --max_cutting_duration [1-17]
                         The maximum allowed cutting duration. It should be between 1 and 17.
 
@@ -269,7 +270,7 @@ tafrigh "https://youtu.be/Di0vcmnxULs" \
 
 ```
 tafrigh "https://youtu.be/dDzxYcEJbgo" \
-  --wit_client_access_token XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
+  --wit_client_access_tokens XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
   --output_dir . \
   --output_formats txt srt \
   --min_words_per_segment 10 \
@@ -280,7 +281,7 @@ tafrigh "https://youtu.be/dDzxYcEJbgo" \
 
 ```
 tafrigh "https://youtube.com/playlist?list=PLyS-PHSxRDxsLnVsPrIwnsHMO5KgLz7T5" \
-  --wit_client_access_token XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
+  --wit_client_access_tokens XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
   --output_dir . \
   --output_formats txt srt \
   --min_words_per_segment 10 \
@@ -291,7 +292,7 @@ tafrigh "https://youtube.com/playlist?list=PLyS-PHSxRDxsLnVsPrIwnsHMO5KgLz7T5" \
 
 ```
 tafrigh "https://youtu.be/4h5P7jXvW98" "https://youtu.be/jpfndVSROpw" \
-  --wit_client_access_token XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
+  --wit_client_access_tokens XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX \
   --output_dir . \
   --output_formats txt srt \
   --min_words_per_segment 10 \