Mirror onnx-community/moonshine-tiny-ONNX (Useful Sensors, MIT)

README.md

@@ -0,0 +1,49 @@
+---
+license: mit
+language:
+- en
+library_name: onnx-asr
+tags:
+- onnx
+- onnx-asr
+- automatic-speech-recognition
+- moonshine
+base_model: UsefulSensors/moonshine-tiny
+---
+
+# Moonshine Tiny (ONNX)
+
+Moonshine Tiny is a compact English speech-to-text model from
+[Useful Sensors](https://github.com/usefulsensors/moonshine). It is an
+encoder-decoder model that reads the raw 16 kHz waveform, so it needs no
+log-mel preprocessor.
+
+This repository is a mirror of the official ONNX export
+[onnx-community/moonshine-tiny-ONNX](https://huggingface.co/onnx-community/moonshine-tiny-ONNX),
+kept so that the OpenVoiceOS ONNX ASR collection is self-contained. The
+weights are unchanged.
+
+## Usage
+
+```py
+import onnx_asr
+
+model = onnx_asr.load_model("moonshine-tiny")
+print(model.recognize("test.wav"))
+```
+
+Quantized variants load with the `quantization` argument:
+
+```py
+model = onnx_asr.load_model("moonshine-tiny", quantization="quantized")
+```
+
+## Credits
+
+Model by Useful Sensors Inc., released under the MIT license. Paper:
+[Moonshine: Speech Recognition for Live Transcription and Voice Commands](https://arxiv.org/abs/2410.15608).
+ONNX export by [onnx-community](https://huggingface.co/onnx-community).
+
+## License
+
+MIT

config.json

@@ -0,0 +1,34 @@
+{
+  "architectures": [
+    "MoonshineForConditionalGeneration"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "decoder_hidden_act": "silu",
+  "decoder_num_attention_heads": 8,
+  "decoder_num_hidden_layers": 6,
+  "decoder_num_key_value_heads": 8,
+  "decoder_start_token_id": 1,
+  "encoder_hidden_act": "gelu",
+  "encoder_num_attention_heads": 8,
+  "encoder_num_hidden_layers": 6,
+  "encoder_num_key_value_heads": 8,
+  "eos_token_id": 2,
+  "hidden_size": 288,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "is_encoder_decoder": true,
+  "max_position_embeddings": 512,
+  "model_type": "moonshine",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "num_key_value_heads": 8,
+  "partial_rotary_factor": 0.9,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.0.dev0"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19dfea5cba225eb38c0dc7b6e6b9464da6cb46266eab7dbcc8f3d5f9a5f5d79e
+size 77906761

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4131cef00b62942e9cdef691101f2cc7dbbcd828d71eee8c6c46c28fd051d6cb
+size 78227550

onnx/decoder_model_merged_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:235addb963ef3997766bc126c3f16561a72370c7c797238e96940c4f76f2c69a
+size 76250574

onnx/decoder_model_merged_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd126e9e95c62b2236116f676f80877ddde488599631014149f92196cd8ae3a7
+size 20189512

onnx/decoder_model_merged_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:451510e9bc0d4d829e50f4feffda384a38fd0a7cc8aee72667b8fdb1fb4c7e08
+size 44650684

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed87831c3a6103534aae7d47a5d485025c659a1323901513961c39fe8a1a367
+size 20243286

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebbdfd5dacc138a78ca3904d2305335687dd5dbc4daae09b2a7affaac8149789
+size 73867894

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbbf580f703b2af2137e0f6d14cd87f31cc67bd858bfd8715403a9489982d1a5
+size 30882331

onnx/encoder_model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbec5181641f717611fc641ff7e261b4ee7b538e307c39e57e38f617a294d6e
+size 15520007

onnx/encoder_model_int8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2981b85cfd6a4647ec37fe139e268cbc2c8a24102bf1fbb70dedeb7964995be8
+size 7919835

onnx/encoder_model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f4c63779321f20e880148d677a7aeccaa8ac572ec5c8de1e53337915b26f26a
+size 10732274

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6fc4b7bc5af75c0591fd157a1f3829b533d18e9769a888fd95a62e470dd4f4a
+size 7937661

preprocessor_config.json

@@ -0,0 +1,5 @@
+{
+  "feature_extractor_type": "MoonshineFeatureExtractor",
+  "processor_class": "MoonshineProcessor",
+  "sampling_rate": 16000
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{}