Initial commit

README.md

@@ -0,0 +1,98 @@
+# GigaAM ASR for ONNX
+## Project purpose:
+Usage of a latest (v3) versions of a GigaAMASR without additional dependencies and localy stored models
+
+## Project setup:
+1. Set up original GigaAM project
+```bash
+# Clone original GigaAM repo:
+git clone https://github.com/salute-developers/GigaAM
+cd GigaAM
+
+# Create temp venv:
+python -m venv ./tmp_venv
+source ./tmp_venv/bin/activate
+
+# Install project:
+pip install -e .
+```
+2. Acquire chosen models:
+```python
+import gigaam
+onnx_dir = '/target/onnx/model/paths'
+model_version = 'v3_ctc'  # Options: v3_* models
+
+model = gigaam.load_model(model_version)
+model.to_onnx(dir_path=onnx_dir)
+```
+3. Fetch tokenizer SentencePieceProcessor model from cache
+- From `~/.cache/gigaam/{model_name}_tokenizer.model`
+- From `https://cdn.chatwm.opensmodel.sberdevices.ru/GigaAM/{model_name}_tokenizer.model`
+4. Then you may remove original project:
+```bash
+cd ..
+rm -r ./GigaAM
+```
+5. Install this (gigaam-onnx) project
+6. Set up onnx runtime and load chosen model:
+```python
+import onnxruntime as ort
+from gigaam_onnx import GigaAMV3E2ERNNT, GigaAMV3RNNT, GigaAMV3E2ECTC, GigaAMV3CTC
+import numpy as np
+
+# Set up ONNX runtime
+if 'CUDAExecutionProvider' in ort.get_available_providers():
+    provider = 'CUDAExecutionProvider'
+else:
+    provider = 'CPUExecutionProvider"
+opts = ort.SessionOptions()
+opts.intra_op_num_threads = 16
+opts.execution_mode = ort.ExecutionMode.ORT_SEQUENTIAL
+opts.log_severity_level = 3
+
+e2e_rnnt_model = GigaAMV3E2ERNNT(
+    '/path/to/onnx/files/v3_e2e_rnnt_decoder.onnx',
+    '/path/to/onnx/files/v3_e2e_rnnt_encoder.onnx',
+    '/path/to/onnx/files/v3_e2e_rnnt_joint.onnx',
+    '/path/to/onnx/files/v3_e2e_rnnt_tokenizer.model',
+    provider,
+    opts
+)
+
+rnnt_model = GigaAMV3RNNT(
+    '/path/to/onnx/files/v3_rnnt_decoder.onnx',
+    '/path/to/onnx/files/v3_rnnt_encoder.onnx',
+    '/path/to/onnx/files/v3_rnnt_joint.onnx',
+    provider,
+    opts
+)
+
+e2e_ctc_model = GigaAMV3E2ECTC(
+    '/path/to/onnx/files/v3_e2e_ctc.onnx',
+    '/path/to/onnx/files/v3_e2e_ctc_tokenizer.model',
+    provider,
+    opts
+)
+
+ctc_model = GigaAMV3CTC(
+    '/path/to/onnx/files/v3_ctc.onnx',
+    provider,
+    opts
+)
+
+# Load wav 16kHz mono PCM
+wav_data = ...
+audio_array = np.array(wav_data)
+
+# Single fragment transcribing with per-char timings 
+text, timings = ctc_model.transcribe(audio_array)
+
+# Batch transcribing with per-char timings
+text, timings = e2e_ctc_model.transcribe_batch([audio_array])[0]
+
+# Batch joined transcribing - joins fragments by lengts provided and returns continuous text with per-char timings
+text, timings = e2e_rnnt_model.transcribe_batch(
+    [audio_array]  # audio chunks
+    [1]  # length of chunks to combine
+)[0]
+```