Merge branch 'main' of https://huggingface.co/spaces/aadnk/whisper-webui

README.md

@@ -54,11 +54,15 @@ When more than one file is processed, the UI will also generate a "All_Output" z
 
 ## Diarization
 
-To detect different speakers in the audio, you can use the [whisper-diarization](https://gitlab.com/aadnk/whisper-diarization) application. 
+To detect different speakers in the audio, you can use the [whisper-diarization](https://gitlab.com/aadnk/whisper-diarization) application, or check "Diarization" in the options.
 
 Download the JSON file after running Whisper on an audio file, and then run app.py in the 
 whisper-diarization repository with the audio file and the JSON file as arguments.
 
+## Translation
+
+To translate the transcript to English, set the task to "Translate". You can also use ChatGPT for this task via my [translate-gpt](https://gitlab.com/aadnk/translate-gpt) CLI application.
+
 ## Whisper Implementation
 
 You can choose between using `whisper` or `faster-whisper`. [Faster Whisper](https://github.com/guillaumekln/faster-whisper) as a drop-in replacement for the 

config.json5

@@ -22,10 +22,18 @@
             "name": "large",
             "url": "large"
         },
+        {
+            "name": "large-v1",
+            "url": "large-v1"
+        },
         {
             "name": "large-v2",
             "url": "large-v2"
         },
+        {
+            "name": "large-v3",
+            "url": "large-v3"
+        },
         // Uncomment to add custom Japanese models
         // NOTE: For Faster-Whisper, the models must be converted to the CTranslate2 format,
         //       see https://github.com/guillaumekln/faster-whisper#model-conversion
@@ -153,4 +161,4 @@
     "diarization_max_speakers": 8,
     // The number of seconds before inactivate processes are terminated. Use 0 to close processes immediately, or None for no timeout.
     "diarization_process_timeout": 60,
-}
+}

src/whisper/fasterWhisperContainer.py

@@ -43,11 +43,11 @@ class FasterWhisperContainer(AbstractWhisperContainer):
         model_url = model_config.url
 
         if model_config.type == "whisper":
-            if model_url not in ["tiny", "base", "small", "medium", "large", "large-v1", "large-v2"]:
+            if model_url not in ["tiny", "base", "small", "medium", "large", "large-v1", "large-v2", "large-v3"]:
                 raise Exception("FasterWhisperContainer does not yet support Whisper models. Use ct2-transformers-converter to convert the model to a faster-whisper model.")
             if model_url == "large":
-                # large is an alias for large-v1
-                model_url = "large-v1"
+                # large is an alias for large-v3
+                model_url = "large-v3"
 
         device = self.device