Update README.md

README.md

@@ -53,7 +53,7 @@ It models audio as tokens and can generate high-quality audio with consistent st
 
 1. Extremely small, based on GPT-2 small architecture. The methodology can be extended to any autoregressive transformer-based architecture.
 2. Ultra-fast. Using our [self hosted service option](#self-hosted-service), on RTX6000Ada NVIDIA GPU the model can achieve speeds up to 400 toks/s (4s of audio generation per s) and under 20ms time to first token.
-3. On RTX6000Ada, it can support a batch size of 1k with full context length of 1024 tokens
+3. On RTX6000Ada, it can support a batch size of ~1000 sequences with full context length of 1024 tokens
 4. Supports voice cloning with small prompts (<5s).
 5. Code mixing text input in 2 languages - English and Hindi.
 
@@ -62,7 +62,7 @@ It models audio as tokens and can generate high-quality audio with consistent st
 1. Model Type: GPT-2 based language model
 2. Size: 124M parameters
 3. Language Support: English, Hindi
-4. License: This model is not for commercial use. This is only a research showcase.
+4. License: This model is not for commercial usage. This is only a research showcase.
 
 ## Technical details