Update tiny models for CohereAsrModel

config.json

@@ -0,0 +1,52 @@
+{
+  "architectures": [
+    "CohereAsrModel"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 4,
+  "decoder_start_token_id": 85,
+  "dtype": "float32",
+  "encoder_config": {
+    "activation_dropout": 0.0,
+    "attention_bias": true,
+    "attention_dropout": 0.0,
+    "conv_kernel_size": 9,
+    "convolution_bias": true,
+    "dropout": 0.0,
+    "dropout_positions": 0.0,
+    "hidden_act": "silu",
+    "hidden_size": 16,
+    "initializer_range": 0.02,
+    "intermediate_size": 32,
+    "layerdrop": 0.0,
+    "max_position_embeddings": 5000,
+    "model_type": "parakeet_encoder",
+    "num_attention_heads": 2,
+    "num_hidden_layers": 2,
+    "num_key_value_heads": 2,
+    "num_mel_bins": 8,
+    "scale_input": false,
+    "subsampling_conv_channels": 8,
+    "subsampling_conv_kernel_size": 3,
+    "subsampling_conv_stride": 2,
+    "subsampling_factor": 4
+  },
+  "eos_token_id": 3,
+  "head_dim": 8,
+  "hidden_act": "relu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 1024,
+  "model_type": "cohere_asr",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pad_token_id": 2,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 16384
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e980343bc81d9ef2c1b80e599e4db81015fe42228839ec9a639045f19db82e4
+size 1198240

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "auto_map": {
+    "AutoFeatureExtractor": "processing_cohere_asr.CohereAsrFeatureExtractor"
+  },
+  "dither": 1e-05,
+  "feature_extractor_type": "CohereAsrFeatureExtractor",
+  "feature_size": 128,
+  "frame_splicing": 1,
+  "hop_length": 160,
+  "log": true,
+  "max_audio_clip_s": 35.0,
+  "min_energy_window_samples": 1600,
+  "n_fft": 512,
+  "n_window_size": 400,
+  "n_window_stride": 160,
+  "normalize": "per_feature",
+  "overlap_chunk_second": 5.0,
+  "pad_to": 0,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "preemphasis": 0.97,
+  "return_attention_mask": true,
+  "sampling_rate": 16000,
+  "win_length": 400
+}

tokenizer_config.json

@@ -0,0 +1,274 @@
+{
+  "add_prefix_space": false,
+  "auto_map": {
+    "AutoTokenizer": [
+      "tokenization_cohere_asr.CohereAsrTokenizer",
+      null
+    ]
+  },
+  "backend": "tokenizers",
+  "bos_token": "<|startoftranscript|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": [
+    "<|nospeech|>",
+    "<|pnc|>",
+    "<|nopnc|>",
+    "<|startofcontext|>",
+    "<|itn|>",
+    "<|noitn|>",
+    "<|timestamp|>",
+    "<|notimestamp|>",
+    "<|diarize|>",
+    "<|nodiarize|>",
+    "<|spkchange|>",
+    "<|audioseparator|>",
+    "<|emo:undefined|>",
+    "<|emo:neutral|>",
+    "<|emo:happy|>",
+    "<|emo:sad|>",
+    "<|emo:angry|>",
+    "<|unklang|>",
+    "<|aa|>",
+    "<|ab|>",
+    "<|af|>",
+    "<|ak|>",
+    "<|sq|>",
+    "<|am|>",
+    "<|ar|>",
+    "<|an|>",
+    "<|hy|>",
+    "<|as|>",
+    "<|av|>",
+    "<|ae|>",
+    "<|ay|>",
+    "<|az|>",
+    "<|bm|>",
+    "<|ba|>",
+    "<|eu|>",
+    "<|be|>",
+    "<|bn|>",
+    "<|bi|>",
+    "<|bs|>",
+    "<|br|>",
+    "<|bg|>",
+    "<|my|>",
+    "<|ca|>",
+    "<|ch|>",
+    "<|ce|>",
+    "<|ny|>",
+    "<|zh|>",
+    "<|cu|>",
+    "<|cv|>",
+    "<|kw|>",
+    "<|co|>",
+    "<|cr|>",
+    "<|hr|>",
+    "<|cs|>",
+    "<|da|>",
+    "<|dv|>",
+    "<|nl|>",
+    "<|dz|>",
+    "<|en|>",
+    "<|eo|>",
+    "<|et|>",
+    "<|ee|>",
+    "<|fo|>",
+    "<|fj|>",
+    "<|fi|>",
+    "<|fr|>",
+    "<|fy|>",
+    "<|ff|>",
+    "<|gd|>",
+    "<|gl|>",
+    "<|lg|>",
+    "<|ka|>",
+    "<|de|>",
+    "<|el|>",
+    "<|kl|>",
+    "<|gn|>",
+    "<|gu|>",
+    "<|ht|>",
+    "<|ha|>",
+    "<|he|>",
+    "<|hz|>",
+    "<|hi|>",
+    "<|ho|>",
+    "<|hu|>",
+    "<|is|>",
+    "<|io|>",
+    "<|ig|>",
+    "<|id|>",
+    "<|ia|>",
+    "<|ie|>",
+    "<|iu|>",
+    "<|ik|>",
+    "<|ga|>",
+    "<|it|>",
+    "<|ja|>",
+    "<|jv|>",
+    "<|kn|>",
+    "<|kr|>",
+    "<|ks|>",
+    "<|kk|>",
+    "<|km|>",
+    "<|ki|>",
+    "<|rw|>",
+    "<|ky|>",
+    "<|kv|>",
+    "<|kg|>",
+    "<|ko|>",
+    "<|kj|>",
+    "<|ku|>",
+    "<|lo|>",
+    "<|la|>",
+    "<|lv|>",
+    "<|li|>",
+    "<|ln|>",
+    "<|lt|>",
+    "<|lu|>",
+    "<|lb|>",
+    "<|mk|>",
+    "<|mg|>",
+    "<|ms|>",
+    "<|ml|>",
+    "<|mt|>",
+    "<|gv|>",
+    "<|mi|>",
+    "<|mr|>",
+    "<|mh|>",
+    "<|mn|>",
+    "<|na|>",
+    "<|nv|>",
+    "<|nd|>",
+    "<|nr|>",
+    "<|ng|>",
+    "<|ne|>",
+    "<|no|>",
+    "<|nb|>",
+    "<|nn|>",
+    "<|oc|>",
+    "<|oj|>",
+    "<|or|>",
+    "<|om|>",
+    "<|os|>",
+    "<|pi|>",
+    "<|ps|>",
+    "<|fa|>",
+    "<|pl|>",
+    "<|pt|>",
+    "<|pa|>",
+    "<|qu|>",
+    "<|ro|>",
+    "<|rm|>",
+    "<|rn|>",
+    "<|ru|>",
+    "<|se|>",
+    "<|sm|>",
+    "<|sg|>",
+    "<|sa|>",
+    "<|sc|>",
+    "<|sr|>",
+    "<|sn|>",
+    "<|sd|>",
+    "<|si|>",
+    "<|sk|>",
+    "<|sl|>",
+    "<|so|>",
+    "<|st|>",
+    "<|es|>",
+    "<|su|>",
+    "<|sw|>",
+    "<|ss|>",
+    "<|sv|>",
+    "<|tl|>",
+    "<|ty|>",
+    "<|tg|>",
+    "<|ta|>",
+    "<|tt|>",
+    "<|te|>",
+    "<|th|>",
+    "<|bo|>",
+    "<|ti|>",
+    "<|to|>",
+    "<|ts|>",
+    "<|tn|>",
+    "<|tr|>",
+    "<|tk|>",
+    "<|tw|>",
+    "<|ug|>",
+    "<|uk|>",
+    "<|ur|>",
+    "<|uz|>",
+    "<|ve|>",
+    "<|vi|>",
+    "<|vo|>",
+    "<|wa|>",
+    "<|cy|>",
+    "<|wo|>",
+    "<|xh|>",
+    "<|ii|>",
+    "<|yi|>",
+    "<|yo|>",
+    "<|za|>",
+    "<|zu|>",
+    "<|spk0|>",
+    "<|spk1|>",
+    "<|spk2|>",
+    "<|spk3|>",
+    "<|spk4|>",
+    "<|spk5|>",
+    "<|spk6|>",
+    "<|spk7|>",
+    "<|spk8|>",
+    "<|spk9|>",
+    "<|spk10|>",
+    "<|spk11|>",
+    "<|spk12|>",
+    "<|spk13|>",
+    "<|spk14|>",
+    "<|spk15|>",
+    "<|spltoken0|>",
+    "<|spltoken1|>",
+    "<|spltoken2|>",
+    "<|spltoken3|>",
+    "<|spltoken4|>",
+    "<|spltoken5|>",
+    "<|spltoken6|>",
+    "<|spltoken7|>",
+    "<|spltoken8|>",
+    "<|spltoken9|>",
+    "<|spltoken10|>",
+    "<|spltoken11|>",
+    "<|spltoken12|>",
+    "<|spltoken13|>",
+    "<|spltoken14|>",
+    "<|spltoken15|>",
+    "<|spltoken16|>",
+    "<|spltoken17|>",
+    "<|spltoken18|>",
+    "<|spltoken19|>",
+    "<|spltoken20|>",
+    "<|spltoken21|>",
+    "<|spltoken22|>",
+    "<|spltoken23|>",
+    "<|spltoken24|>",
+    "<|spltoken25|>",
+    "<|spltoken26|>",
+    "<|spltoken27|>",
+    "<|spltoken28|>",
+    "<|spltoken29|>",
+    "<|spltoken30|>",
+    "<|spltoken31|>",
+    "<|spltoken32|>",
+    "<|spltoken33|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "split_special_tokens": true,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}