Updated handler for language detection

handler.py

@@ -2,8 +2,8 @@
 from typing import Dict, Any, List
 from transformers import pipeline
 import torch
-from io import BytesIO
 import base64
+import json
 
 
 class EndpointHandler:
@@ -22,6 +22,8 @@ class EndpointHandler:
             device=device,
             chunk_length_s=30,
             )
+        with open("token_mapping.json") as file:
+            self.token_mapping = json.load(file)
 
 
     def __call__(self, data: Dict[str, Any]) -> List[Dict[str, Any]]:
@@ -35,14 +37,19 @@ class EndpointHandler:
         """
         inputs = data["inputs"]
         audio = base64.b64decode(inputs["audio"])  # bytes
-        lang = inputs["language"]
+        lang = inputs["language"]  # ISO code
         task = inputs["task"]  # One of "translate", "transcribe"
 
-        # Set language and task
-        self.pipeline.model.config.forced_decoder_ids = self.pipeline.tokenizer.get_decoder_prompt_ids(language=lang, task=task)
-        self.pipeline
-
+        # Set language and task (order: language, task, timestamp)
+        if lang is None:
+            lang_id = None  # line 1576, https://github.com/huggingface/transformers/blob/v4.27.2/src/transformers/models/whisper/modeling_whisper.py
+        else:
+            lang_id = self.token_mapping[f"<|{lang}|>"]
+        task_id = self.token_mapping[f"<|{task}|>"]
+        timestamp_id = self.token_mapping["<|notimestamps|>"]  # Required to output timestamps
+        forced_ids = [(1, lang_id), (2, task_id), (3, timestamp_id)]
+        
         # Model inference
-        output = self.pipeline(audio, return_timestamps="word")
+        output = self.pipeline(audio, return_timestamps="word", generate_kwargs={"forced_decoder_ids": forced_ids})
 
         return output

token_mapping.json

@@ -0,0 +1,108 @@
+{
+    "<|af|>": 50327,
+    "<|am|>": 50334,
+    "<|ar|>": 50272,
+    "<|as|>": 50350,
+    "<|az|>": 50304,
+    "<|ba|>": 50355,
+    "<|be|>": 50330,
+    "<|bg|>": 50292,
+    "<|bn|>": 50302,
+    "<|bo|>": 50347,
+    "<|br|>": 50309,
+    "<|bs|>": 50315,
+    "<|ca|>": 50270,
+    "<|cs|>": 50283,
+    "<|cy|>": 50297,
+    "<|da|>": 50285,
+    "<|de|>": 50261,
+    "<|el|>": 50281,
+    "<|en|>": 50259,
+    "<|es|>": 50262,
+    "<|et|>": 50307,
+    "<|eu|>": 50310,
+    "<|fa|>": 50300,
+    "<|fi|>": 50277,
+    "<|fo|>": 50338,
+    "<|fr|>": 50265,
+    "<|gl|>": 50319,
+    "<|gu|>": 50333,
+    "<|haw|>": 50352,
+    "<|ha|>": 50354,
+    "<|he|>": 50279,
+    "<|hi|>": 50276,
+    "<|hr|>": 50291,
+    "<|ht|>": 50339,
+    "<|hu|>": 50286,
+    "<|hy|>": 50312,
+    "<|id|>": 50275,
+    "<|is|>": 50311,
+    "<|it|>": 50274,
+    "<|ja|>": 50266,
+    "<|jw|>": 50356,
+    "<|ka|>": 50329,
+    "<|kk|>": 50316,
+    "<|km|>": 50323,
+    "<|kn|>": 50306,
+    "<|ko|>": 50264,
+    "<|la|>": 50294,
+    "<|lb|>": 50345,
+    "<|ln|>": 50353,
+    "<|lo|>": 50336,
+    "<|lt|>": 50293,
+    "<|lv|>": 50301,
+    "<|mg|>": 50349,
+    "<|mi|>": 50295,
+    "<|mk|>": 50308,
+    "<|ml|>": 50296,
+    "<|mn|>": 50314,
+    "<|mr|>": 50320,
+    "<|ms|>": 50282,
+    "<|mt|>": 50343,
+    "<|my|>": 50346,
+    "<|ne|>": 50313,
+    "<|nl|>": 50271,
+    "<|nn|>": 50342,
+    "<|nocaptions|>": 50362,
+    "<|notimestamps|>": 50363,
+    "<|no|>": 50288,
+    "<|oc|>": 50328,
+    "<|pa|>": 50321,
+    "<|pl|>": 50269,
+    "<|ps|>": 50340,
+    "<|pt|>": 50267,
+    "<|ro|>": 50284,
+    "<|ru|>": 50263,
+    "<|sa|>": 50344,
+    "<|sd|>": 50332,
+    "<|si|>": 50322,
+    "<|sk|>": 50298,
+    "<|sl|>": 50305,
+    "<|sn|>": 50324,
+    "<|so|>": 50326,
+    "<|sq|>": 50317,
+    "<|sr|>": 50303,
+    "<|startoflm|>": 50360,
+    "<|startofprev|>": 50361,
+    "<|startoftranscript|>": 50258,
+    "<|su|>": 50357,
+    "<|sv|>": 50273,
+    "<|sw|>": 50318,
+    "<|ta|>": 50287,
+    "<|te|>": 50299,
+    "<|tg|>": 50331,
+    "<|th|>": 50289,
+    "<|tk|>": 50341,
+    "<|tl|>": 50348,
+    "<|transcribe|>": 50359,
+    "<|translate|>": 50358,
+    "<|tr|>": 50268,
+    "<|tt|>": 50351,
+    "<|uk|>": 50280,
+    "<|ur|>": 50290,
+    "<|uz|>": 50337,
+    "<|vi|>": 50278,
+    "<|yi|>": 50335,
+    "<|yo|>": 50325,
+    "<|zh|>": 50260
+  }