Speech To Text
Speech To Text (or Automatic speech recognition) models can transcribe and translate speech into text. They can be used for AI assistants and conversational AI applications. We provide the wrapping code for streaming efficiency of Speech To Text models. For the i.MX 95 microprocessing unit (MPU), we support Neutron neural processing unit (NPU) acceleration.
软件详情
支持的器件
- i.MX8MPLUS: i.MX 8M Plus – Arm® Cortex®-A53，机器学习，视觉，多媒体和工业物联网
- i.MX93: i.MX 93应用处理器系列——Arm® Cortex®-A55，ML加速，高能效MPU
- i.MX95: i.MX 95应用处理器系列：支持功能安全的高性能平台，配备eIQ® Neutron NPU
系统需求
Models supported: Moonshine-tiny, Moonshine-base, Whisper-tiny.en, Whisper-base.en, Whisper-small.en and Whisper-medium.en
i.MX 95
| Model | Model size [parameters] | Weights format | WER* [%] | Cores | Time To First Token** [seconds] | Full transcription latency following X seconds of speech [seconds] | Library dependency | ||
|---|---|---|---|---|---|---|---|---|---|
| X = 3s | X = 6s | X = 9s | |||||||
| Moonshine-tiny | 27M | Q8 | 5.79 | 6x Cortex-A55 | 0.17 | 0.38 | 0.58 | 0.84 | ONNX |
| Moonshine-base | 61M | Q8 | 4.34 | 6x Cortex-A55 | 0.3 | 0.56 | 0.89 | 1.52 | ONNX |
| Whisper-tiny.en | 39M | Q8 | 7.11 | 6x Cortex-A55 + NPU | 0.17 | 0.33 | 0.5 | 0.79 | ONNX |
| Whisper-base.en | 74M | Q8 | 5.32 | 6x Cortex-A55 + NPU | 0.27 | 0.5 | 0.78 | 1.17 | ONNX |
| Whisper-small.en | 244M | Q8 | 3.77 | 6x Cortex-A55 + NPU | 0.5 | 1.04 | 1.86 | 2.37 | ONNX |
| Whisper-Medium.en | 769M | Q8 | 3.93 | 6x Cortex-A55 + NPU | 1.16 | 2.53 | 3.66 | 5.6 | ONNX |
i.MX 93
| Model | Model size [parameters] | Weights format | WER* [%] | Cores | Time To First Token** [seconds] | Full transcription latency following X seconds of speech [seconds] | Library dependency | ||
|---|---|---|---|---|---|---|---|---|---|
| X = 3s | X = 6s | X = 9s | |||||||
| Moonshine-tiny | 27M | Q8 | 5.79 | 2x Cortex-A55 | 0.29 | 0.53 | 0.89 | 1.39 | ONNX |
| Moonshine-base | 61M | Q8 | 4.34 | 2x Cortex-A55 | 0.54 | 0.94 | 1.58 | 2.76 | ONNX |
| Whisper-tiny.en | 39M | Q8 | 7.11 | 2x Cortex-A55 | 0.27 | 0.53 | 0.93 | 1.38 | ONNX |
| Whisper-base.en | 74M | Q8 | 5.32 | 2x Cortex-A55 | 0.5 | 0.9 | 1.62 | 2.43 | ONNX |
| Whisper-small.en | 244M | Q8 | 3.77 | 2x Cortex-A55 | 1.45 | 2.47 | 4.75 | 6.45 | ONNX |
i.MX 8M Plus
| Model | Model size [parameters] | Weights format | WER* [%] | Cores | Time To First Token** [seconds] | Full transcription latency following X seconds of speech [seconds] | Library dependency | ||
|---|---|---|---|---|---|---|---|---|---|
| X = 3s | X = 6s | X = 9s | |||||||
| Moonshine-tiny | 27M | Q8 | 5.79 | 4x Cortex-A53 | 0.23 | 0.45 | 0.78 | 1.12 | ONNX |
| Moonshine-base | 61M | Q8 | 4.34 | 4x Cortex-A53 | 0.42 | 0.76 | 1.28 | 1.99 | ONNX |
| Whisper-tiny.en | 39M | Q8 | 7.11 | 4x Cortex-A53 | 0.21 | 0.44 | 0.73 | 0.99 | ONNX |
| Whisper-base.en | 74M | Q8 | 5.32 | 4x Cortex-A53 | 0.42 | 0.73 | 1.27 | 1.74 | ONNX |
| Whisper-small.en | 244M | Q8 | 3.77 | 4x Cortex-A53 | 1.4 | 2.11 | 3.83 | 5.51 | ONNX |
