-
I used the Lora fine-tuning configure from the Aishell recipe to tune Whisper. After I finished training, when I tried to use the Speech2Text class to infer any audio:
> from espnet2.bin.asr_infer…
-
Hi I tried the hf demo of maskgct and also deployed it on my local server.
I noticed that on Huggingface demo page, the user only needs to input the prompt audio and target text, but in the exampl…
-
cuda version11.8
File "/App/install/OPS/pyenv/ai-speech/lib/python3.10/site-packages/transformers/pipelines/base.py", line 1112, in forward
model_outputs = self._forward(model_inputs, **forwa…
-
hello I'm trying to fine-tune small model for ASR for custom Egyptian dataset
How can I do it ?
here's a data sample of my custom data, is it in right format?
![Screenshot from 2024-01-18 14-15-11…
-
### Feature request
Current Whisper inference works well with specified language. However, it does not support passing `language=None`, which can detect the language automatically. A `RuntimeError` i…
-
## General Question
tts服务是成功的，asr报错 509
-
param(
[string] $VaultSubscriptionId = 'xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx',
[string] $VaultResourceGroupName = 'secdrtestrg',
[string] $vmResourceGroupName = 'primaryDRtestrg',
…
-
```diff
diff --git a/src/libasr/ASR.asdl b/src/libasr/ASR.asdl
index d1356151b..72982ac12 100644
--- a/src/libasr/ASR.asdl
+++ b/src/libasr/ASR.asdl
@@ -19,7 +19,6 @@ symbol
| EnumType(symb…
-
I have downloaded the Faster Whisper ASR models in the tools/asr/models/ folder but still fail to load them .. only encounter with the resource_tracker warning and not going further. I have tried v2…
-
Hi,
I noticed an issue when converting a Transducer model from espnet to espnet_onnx where the ```max_seq_len``` in the ```DefaultEncoder``` class was not properly set when specifying ```m.set_expo…