Release v1.0 — whisper-small-malayalam, WER 37.64%

generation_config.json

@@ -41,22 +41,13 @@
       5
     ]
   ],
-  "assistant_confidence_threshold": 0.4,
-  "assistant_lookbehind": 10,
   "begin_suppress_tokens": [
     220,
     50257
   ],
   "bos_token_id": 50257,
   "decoder_start_token_id": 50258,
-  "diversity_penalty": 0.0,
-  "do_sample": false,
-  "early_stopping": false,
-  "encoder_no_repeat_ngram_size": 0,
-  "encoder_repetition_penalty": 1.0,
   "eos_token_id": 50257,
-  "epsilon_cutoff": 0.0,
-  "eta_cutoff": 0.0,
   "forced_decoder_ids": null,
   "is_multilingual": true,
   "lang_to_id": {
@@ -161,23 +152,11 @@
     "<|zh|>": 50260
   },
   "language": "malayalam",
-  "length_penalty": 1.0,
   "max_initial_timestamp_index": 50,
   "max_length": 448,
-  "min_length": 0,
-  "no_repeat_ngram_size": 0,
   "no_timestamps_token_id": 50363,
-  "num_assistant_tokens": 20,
-  "num_assistant_tokens_schedule": "constant",
-  "num_beam_groups": 1,
-  "num_beams": 1,
-  "num_return_sequences": 1,
-  "output_scores": false,
   "pad_token_id": 50257,
   "prev_sot_token_id": 50361,
-  "remove_invalid_values": false,
-  "repetition_penalty": 1.0,
-  "return_dict_in_generate": false,
   "return_timestamps": false,
   "suppress_tokens": [
     1,
@@ -269,16 +248,10 @@
     50361,
     50362
   ],
-  "target_lookbehind": 10,
   "task": "transcribe",
   "task_to_id": {
     "transcribe": 50359,
     "translate": 50358
   },
-  "temperature": 1.0,
-  "top_k": 50,
-  "top_p": 1.0,
-  "transformers_version": "5.0.0",
-  "typical_p": 1.0,
-  "use_cache": true
+  "transformers_version": "5.0.0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf4160946b6a1171664f85c219c10501cdc701c63fb024da73faad400d3bd1b
+oid sha256:de719523b46e8b2666b0f01e436e9681a931d6561950fdd0812d404f76d8abb6
 size 966995080

processor_config.json

@@ -0,0 +1,17 @@
+{
+  "feature_extractor": {
+    "chunk_length": 30,
+    "dither": 0.0,
+    "feature_extractor_type": "WhisperFeatureExtractor",
+    "feature_size": 80,
+    "hop_length": 160,
+    "n_fft": 400,
+    "n_samples": 480000,
+    "nb_max_frames": 3000,
+    "padding_side": "right",
+    "padding_value": 0.0,
+    "return_attention_mask": false,
+    "sampling_rate": 16000
+  },
+  "processor_class": "WhisperProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,127 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|endoftext|>",
+    "<|startoftranscript|>",
+    "<|en|>",
+    "<|zh|>",
+    "<|de|>",
+    "<|es|>",
+    "<|ru|>",
+    "<|ko|>",
+    "<|fr|>",
+    "<|ja|>",
+    "<|pt|>",
+    "<|tr|>",
+    "<|pl|>",
+    "<|ca|>",
+    "<|nl|>",
+    "<|ar|>",
+    "<|sv|>",
+    "<|it|>",
+    "<|id|>",
+    "<|hi|>",
+    "<|fi|>",
+    "<|vi|>",
+    "<|he|>",
+    "<|uk|>",
+    "<|el|>",
+    "<|ms|>",
+    "<|cs|>",
+    "<|ro|>",
+    "<|da|>",
+    "<|hu|>",
+    "<|ta|>",
+    "<|no|>",
+    "<|th|>",
+    "<|ur|>",
+    "<|hr|>",
+    "<|bg|>",
+    "<|lt|>",
+    "<|la|>",
+    "<|mi|>",
+    "<|ml|>",
+    "<|cy|>",
+    "<|sk|>",
+    "<|te|>",
+    "<|fa|>",
+    "<|lv|>",
+    "<|bn|>",
+    "<|sr|>",
+    "<|az|>",
+    "<|sl|>",
+    "<|kn|>",
+    "<|et|>",
+    "<|mk|>",
+    "<|br|>",
+    "<|eu|>",
+    "<|is|>",
+    "<|hy|>",
+    "<|ne|>",
+    "<|mn|>",
+    "<|bs|>",
+    "<|kk|>",
+    "<|sq|>",
+    "<|sw|>",
+    "<|gl|>",
+    "<|mr|>",
+    "<|pa|>",
+    "<|si|>",
+    "<|km|>",
+    "<|sn|>",
+    "<|yo|>",
+    "<|so|>",
+    "<|af|>",
+    "<|oc|>",
+    "<|ka|>",
+    "<|be|>",
+    "<|tg|>",
+    "<|sd|>",
+    "<|gu|>",
+    "<|am|>",
+    "<|yi|>",
+    "<|lo|>",
+    "<|uz|>",
+    "<|fo|>",
+    "<|ht|>",
+    "<|ps|>",
+    "<|tk|>",
+    "<|nn|>",
+    "<|mt|>",
+    "<|sa|>",
+    "<|lb|>",
+    "<|my|>",
+    "<|bo|>",
+    "<|tl|>",
+    "<|mg|>",
+    "<|as|>",
+    "<|tt|>",
+    "<|haw|>",
+    "<|ln|>",
+    "<|ha|>",
+    "<|ba|>",
+    "<|jw|>",
+    "<|su|>",
+    "<|translate|>",
+    "<|transcribe|>",
+    "<|startoflm|>",
+    "<|startofprev|>",
+    "<|nocaptions|>",
+    "<|notimestamps|>"
+  ],
+  "is_local": false,
+  "language": "malayalam",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "predict_timestamps": false,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "task": "transcribe",
+  "tokenizer_class": "WhisperTokenizer",
+  "unk_token": "<|endoftext|>"
+}