minor fixes
Browse files
README.md
CHANGED
|
@@ -306,7 +306,7 @@ canary_model.change_decoding_strategy(decode_cfg)
|
|
| 306 |
|
| 307 |
Input to canary-180m-flash can be either a list of paths to audio files or a jsonl manifest file.
|
| 308 |
|
| 309 |
-
### Inference with
|
| 310 |
If the input is a list of paths, canary-180m-flash assumes that the audio is English and transcribes it. I.e., canary-180m-flash default behavior is English ASR.
|
| 311 |
```python
|
| 312 |
output = canary_model.transcribe(
|
|
@@ -354,7 +354,7 @@ output = canary_model.transcribe(
|
|
| 354 |
)
|
| 355 |
```
|
| 356 |
|
| 357 |
-
### Longform inference with
|
| 358 |
Canary models are designed to handle input audio smaller than 40 seconds. In order to handle longer audios, NeMo includes [speech_to_text_aed_chunked_infer.py](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_chunked_inference/aed/speech_to_text_aed_chunked_infer.py) script that handles chunking, performs inference on the chunked files, and stitches the transcripts.
|
| 359 |
|
| 360 |
The script will perform inference on all `.wav` files in `audio_dir`. Alternatively you can also pass a path to a manifest file as shown above. The decoded output will be saved at `output_json_path`.
|
|
|
|
| 306 |
|
| 307 |
Input to canary-180m-flash can be either a list of paths to audio files or a jsonl manifest file.
|
| 308 |
|
| 309 |
+
### Inference with canary-180m-flash:
|
| 310 |
If the input is a list of paths, canary-180m-flash assumes that the audio is English and transcribes it. I.e., canary-180m-flash default behavior is English ASR.
|
| 311 |
```python
|
| 312 |
output = canary_model.transcribe(
|
|
|
|
| 354 |
)
|
| 355 |
```
|
| 356 |
|
| 357 |
+
### Longform inference with canary-180m-flash:
|
| 358 |
Canary models are designed to handle input audio smaller than 40 seconds. In order to handle longer audios, NeMo includes [speech_to_text_aed_chunked_infer.py](https://github.com/NVIDIA/NeMo/blob/main/examples/asr/asr_chunked_inference/aed/speech_to_text_aed_chunked_infer.py) script that handles chunking, performs inference on the chunked files, and stitches the transcripts.
|
| 359 |
|
| 360 |
The script will perform inference on all `.wav` files in `audio_dir`. Alternatively you can also pass a path to a manifest file as shown above. The decoded output will be saved at `output_json_path`.
|